Datasets:

Alignment-Lab-AI

/

english-flan

like 0

[ { "from": "human", "value": "Instructions: In this task, based on the given context word, you are asked to create a pair of sentences each containing a blank (_) and their corresponding answer. The sentence pair should look similar, and should be about two related but different objects; for example \"trophy\" and \"suitcase\". Additionally, the two sentences must be different in terms of trigger words (e.g., \"small\" and \"big\") which express contrasting properties about the two objects. The answer must not be associated with the trigger word; instead, it should depend on the context present in twin sentences. Also, the answers should not be ambiguous. For each sentence, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use animals and proper nouns (e.g., New York, Macbook, Jeff Bezos, McDonald's, ...) as your objects. Avoid repeating the same style or phrase in twin sentences. E.g., a contrasting sentence can always be created using simple negation i.e. by adding not, never, etc. Instead, try to increase diversity. Both twin sentences must contain at least 15 and at most 30 words. Twin sentences must have at least 70% overlapping words. You must utilize the given context word while writing the twin sentences. Each of the twin sentences must contain only one blank. Make sure that ObjectX and Y have the same number e.g. when ObjectX is singular, ObjectY must be singular, too. The two objects (ObjectX & ObjectY) should be used ONCE in each sentence. Here is a list of contrastive words that may be used as trigger words. You should create more such trigger words and use them in your twin sentences.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far | \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n\nInput: Context Word: flaxseed.\nOutput:" }, { "from": "gpt", "value": "Sentence 1: Tim wanted to put flaxseed into his smoothie in the blender but the _ was too small. \nAnswer1: flaxseed. \nSentence 2: Tim wanted to put flaxseed into his smoothie in the blender but the _ was too big. \nAnswer2: blender." } ]

[ { "from": "human", "value": "Instructions: In this task you will be given a claim and a perspective. You should determine whether that perspective supports or undermines the claim. If the perspective could possibly convince someone with different view, it is supporting, otherwise it is undermining.\nInput: claim: Children should be allowed to have facebook accounts.\n perspective: Features like parental control and privacy settings make it easier\nOutput:" }, { "from": "gpt", "value": "support" } ]

[ { "from": "human", "value": "You are given a paragraph (Passage), a question (Question) and two answer options (Option1 and Option2). Your task is to find the correct answer (and return the string of the correct option, not option1/2) for the given question from the given options and based on the given passage. Answer of the question can be found directly from the passage.\nQ: Passage: My brother 's birthday party was going to be this Saturday . We sent out invitations in the mail two weeks ago to all of his friends . The invitation asked the guests to call us and let us know if they would come to the party . Most of his friends called to let us know they were going to come . The snow kept coming and coming . We looked at the weather forecast and it said we were getting a blizzard ! When it snows that much , it is not safe to drive . Sadly , we have to cancel the party . We called each friend we had invited on the phone and let them know we were cancelling the party . Most of our friends were pretty sad that the party was canceled , but they agreed the weather was too bad to have a party . We hope to reschedule the party so we can celebrate my brother 's birthday another day when there is no snow . Question: Who did they not want to drive in the snow to get to the party? Option1: Their friends. Option2: Their parents.\nA: " }, { "from": "gpt", "value": "Their friends." } ]

[ { "from": "human", "value": "Teacher: In this task, you need to answer basic science questions. For each question, several terms are intentionally masked with ***. This masking can cover very few or many of the question words. Clearly, if masked terms are important, the modified question will be impossible to answer. Please indicate the correct answer with one of the following responses: \"A\", \"B\", \"C\", \"D\" or \"E\". While \"A\"-\"D\" correspond to the answer options provided in the input, \"E\" represents \"I don't know\" for questions that do not provide enough information. Respond via \"E\" if the question is not answerable. Do not generate anything else apart from one of the following characters: 'A', 'B, 'C', 'D', 'E'.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nQuestion: *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** *** ***. (A) dissolving (B) deposition (C) weathering (D) erosion.\nSolution: E.\nReason: All the words are dropped, so the correct answer should be 'E' that stands for \"I don't know\".\n\nNow, solve this instance: Question: A student *** a *** of *** to a glass of *** water. The *** *** *** (A) increases (B) decrease (C) stay the same (D).\nStudent:" }, { "from": "gpt", "value": "E." } ]

[ { "from": "human", "value": "Given a sentence, generate a new sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.\nQ: If you opt to boost your brand then you should earn some money .\nA: " }, { "from": "gpt", "value": "If you want to farm your family then you should earn some independence ." } ]

[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a sentence or phrase in English. You must translate it to Xhosa in a way that is equivalent in terms of meaning and grammatically correct.\nProblem:Finally because of the resultant increase in the labour involved in assembling the ship it will inevitably be more expensive to build.\nSolution:" }, { "from": "gpt", "value": "Ekugqibeleni ngenxa yeziphumo zonyuko kumsebenzi owenziwayo ekudibaniseni inqanawa iyakube nexabiso eliphezulu ekuyakheni ngokungenakunqandwa." } ]

[ { "from": "human", "value": "Definition: In this task, you're given the title of a five-sentence story, the first four sentences, and two options for the fifth sentence as a and b. Your job is to pick the sentence option that does not connect with the rest of the story, indicating your choice as 'a' or 'b'. If both sentences are plausible, pick the one that makes less sense.\nInput: Title: Learning to swim. Sentence 1: Glenn had never learned to swim as a child. Sentence 2: He wanted to go to the pool with his friends. Sentence 3: His apprehension prevented him from having fun. Sentence 4: One day he went to the pool for private lessons. Choices: a. This gave Glenn the courage to go swimming with his friends. b. The bus got us home by early evening.\nOutput:" }, { "from": "gpt", "value": "b" } ]

[ { "from": "human", "value": "Instructions: In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element in the reverse order. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\nInput: 6, 7, ['C', 'v', 'f', 'A', 'N', '3085', 'E']\nOutput:" }, { "from": "gpt", "value": "E, 3085" } ]

[ { "from": "human", "value": "Detailed Instructions: You will be asked how to do a certain task. You should describe a physical process that does not lead to the asked outcome, yet it is closely related to it (i.e., it should use the words that are provided in the input). The physical process can be moving something, arranging something in a certain way, mixing things, shaking them, etc. To make sure that the generated process does not lead to the asked outcome, you can introduce objects or events unrelated to the context of the question e.g. 'cleaning the keyboard by making an elephant sit on them'; or you can create contradictory statements e.g. 'drying wet keyboards with running water'. In your responses, avoid typos and misspellings.\nQ: How do you bring a pot of water on the stove to a full rolling boil?\nA:" }, { "from": "gpt", "value": "Turn the stove on to its coolest setting, then wait until the water is full of large, strong bubbles." } ]

[ { "from": "human", "value": "Instructions: In this task, you need to provide the parts-of-speech tag of a word present in a sentence specified within curly braces ( '{{ ... }}' ). The parts-of-speech tags are coarse labels that represent a category of words with similar grammatical properties. The list of part-of-speech tags i.e. tagset of this corpus is 'ADJ': Adjectives are words that typically modify nouns and specify their properties or attributes, 'ADP': Adposition is a cover term for prepositions and postpositions, 'ADV': Adverbs are words that typically modify verbs for such categories as time, place, direction or manner, 'AUX': An auxiliary is a function word that accompanies the lexical verb of a verb phrase and expresses grammatical distinctions not carried by the lexical verb, such as person, number, tense, mood, aspect, voice or evidentiality, 'CCONJ': A coordinating conjunction is a word that links words or larger constituents without syntactically subordinating one to the other and expresses a semantic relationship between them, 'DET': Determiners are words that modify nouns or noun phrases and express the reference of the noun phrase in context, 'INTJ': An interjection is a word that is used most often as an exclamation or part of an exclamation, 'NOUN': Nouns are a part of speech typically denoting a person, place, thing, animal or idea, 'NUM': A numeral is a word, functioning most typically as a determiner, adjective or pronoun, that expresses a number and a relation to the number, such as quantity, sequence, frequency or fraction, 'PART': Particles are function words that must be associated with another word or phrase to impart meaning and that do not satisfy definitions of other universal parts of speech, 'PRON': Pronouns are words that substitute for nouns or noun phrases, whose meaning is recoverable from the linguistic or extralinguistic context, 'PROPN': A proper noun is a noun (or nominal content word) that is the name (or part of the name) of a specific individual, place, or object, 'PUNCT': Punctuation marks are non-alphabetical characters and character groups used in many languages to delimit linguistic units in printed text, 'SCONJ': A subordinating conjunction is a conjunction that links constructions by making one of them a constituent of the other. The subordinating conjunction typically marks the incorporated constituent which has the status of a (subordinate) clause, 'SYM': A symbol is a word-like entity that differs from ordinary words by form, function or both, 'VERB': A verb is a member of the syntactic class of words that typically signal events and actions, can constitute a minimal predicate in a clause, and govern the number and types of other constituents which may occur in the clause, 'X': The tag X is used for words that for some reason cannot be assigned a real part-of-speech category.\nInput: Sentence: A Sri Lanka - born Tamil with a Norwegian passport was arrested by Thai authorities in {{ 2000 }} for his links with the LTTE . \nWord: 2000\nOutput:" }, { "from": "gpt", "value": "NUM" } ]

[ { "from": "human", "value": "Craft one correct answer to the question given in input. To make it more interesting, try to use non-stereotypical language if possible. Make sure your correct answer is reasonably long, consistent with the context, and requires common sense (instead of explicit extraction from the context.) In your answer, use as few words as possible from the given context. Use a response that is uncommon/non-stereotypical, so that it is less predictable. To be less repetitive, please vary your language for each question.\n\nExample Input: Context: The Senior Curriculum Developer will be responsible for delivering effectively - written training materials for employees in a sales and service environment , working with other training team members and subject matter experts within the company to do so . In this role , you will help develop the overall plan and structure for training programs , as well as develop and enhance the training materials , which include manuals , course outlines , background materials , workbooks , handouts and course assessments . Delivery will span a variety of modes , including , but not limited to : traditional classroom training , conference calls , eLearning , interactive web - based instruction as well as workshops . \nQuestion: What is being described in this sales pitch ?\nExample Output: Educational materials .\n\nExample Input: Context: We were looking for something spectacular to make the effort worth it . The first of the caves was a sizeable hole in the ground in which there were a few scrubby trees and some rocks . From the smell , it was pretty clear that it was also a nice out of the way spot for ill - prepared tourists to relieve themselves . \nQuestion: How did I get to the cave ?\nExample Output: By a difficult walk through the woods.\n\nExample Input: Context: Well , folks , this was our first day without any real new adventure ( which is ok with Kay ! ) , other than for the first time carefully picking our way in between wing dams ( long piles of rock below the surface to slow or direct downstream current ) outside the channel . The objective , of course , is to present as uninteresting a target as possible to the tows roaring up and down the river . \nQuestion: What may be the reason to travel down the river ?\nExample Output:" }, { "from": "gpt", "value": "They want to have fun adventures with friends .\n\n" } ]

[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nGiven a premise, an initial context, an original ending, and a counterfactual context, the task is to generate a new story ending aligned with the counterfactual context and as close to the original ending as possible. Each instance consists of a five-sentence story. The premise is the first sentence of a story, and the second sentence, which is the initial context, provides more information about the story's context and the story's general plot. The original ending is the last three sentences of the story. Also, a counterfactual context is a slight modification to the initial context. You should write a new story ending that edits the original story ending as little as possible to regain coherence with the counterfactual context. To sum up, you should write the last three sentences of a story based on the premise(first sentence) and the counterfactual context(second sentence) of the story.\nExample: Premise: Susie was sitting on her barstool. \n Initial Context: She kept kicking the counter with her feet. \n Original Ending: Suddenly, her kick sent her falling backwards. The chair hit the ground with a thud and broke. Susie hurt her head and was really scared. \n Counterfactual Context: She kept herself steady with her feet.\nOutput: Suddenly, an earthquake sent her falling backwards. The chair hit the ground with a thud and broke. Susie hurt her head and was really scared.\nThe generated new ending is perfect. It considers the counterfactual context and changes required parts in original ending.\n\nNew input case for you: Premise: John buckled his seat on the biggest roller coaster at the park. \n Initial Context: John felt the huge roller coaster stop abruptly. \n Original Ending: From the top of the hill, John could see the entire amusement park. He was stuck at the top for three hours. John never went on a roller coaster again. \n Counterfactual Context: John felt the huge roller coaster moving quickly but smoothly.\nOutput:" }, { "from": "gpt", "value": "From the top of the hill, John could see the entire amusement park. The whole thing felt like it lasted for three hours. John never went on a roller coaster again. " } ]

[ { "from": "human", "value": "In this task, you are given an input list A. You need to convert all the alphabets in the list with a number representing their position in the English alphabet. E.g., replace A by 1, B by 2, a by 1, b by 2, and so on.\n\n['r', '7053', 'N', 'h', '9529', '3199', 'i', 'Z', '8075', 'h', '1965', '313', 'e', '2279', 'K', '9723', 'U', '3537', 'Y', 'b', 'i', '6289', '4387', 'W', 'N', '9423', '1027', '5745', '9229', 'h']" }, { "from": "gpt", "value": "18, 7053, 14, 8, 9529, 3199, 9, 26, 8075, 8, 1965, 313, 5, 2279, 11, 9723, 21, 3537, 25, 2, 9, 6289, 4387, 23, 14, 9423, 1027, 5745, 9229, 8" } ]

[ { "from": "human", "value": "instruction:\nIn this task you will be given a claim and a perspective. You should determine whether that perspective supports or undermines the claim. If the perspective could possibly convince someone with different view, it is supporting, otherwise it is undermining.\nquestion:\nclaim: Social networking sites are good for our society.\n perspective: Students can be recruited to universities through social media.\nanswer:\nsupport\n\n\nquestion:\nclaim: social networking sites should be banned at the workplaces.\n perspective: Social media enables \"sexting,\" which can lead to criminal charges and the unexpected proliferation of personal images.\nanswer:\nsupport\n\n\nquestion:\nclaim: Children should be allowed to have facebook accounts.\n perspective: Features like parental control and privacy settings make it easier\nanswer:\n" }, { "from": "gpt", "value": "support\n\n\n" } ]

[ { "from": "human", "value": "Given a piece of financial news and its polarity, classify it into 'true' if the polarity is correct and classify into 'false' if the polarity is incorrect. Output must be 'true' or 'false'. \nQ: news:cents Scout for potential acquisition targets , with detailed insight into the companies financial and operational performance .\npolarity:neutral\nA: " }, { "from": "gpt", "value": "true" } ]

[ { "from": "human", "value": "Teacher:Given a sentence, generate a new sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.\nTeacher: Now, understand the problem? Solve this instance: Telling a story requires validation .\nStudent:" }, { "from": "gpt", "value": "Telling a story requires language." } ]

[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you are given a question and a corresponding answer. Your task is to generate a fact statement that is useful in answering the given question.\nExample: Question: Frilled sharks and angler fish live far beneath the surface of the ocean, which is why they are known as? Answer: deep sea fish\nOutput: deep sea animals live deep in the ocean.\nThis sentence is useful when answering the given question. The sentence provides the information that animals who live deep in the ocean are called deep sea fish. This is a good output. \n\nNew input case for you: Question: What fails to work during a power outage? Answer: an electric fan.\nOutput:" }, { "from": "gpt", "value": "electrical devices convert electricity into other forms of energy" } ]

[ { "from": "human", "value": "Construct a question that every answer in the list is correct and reasonable for it.\nOne example is below.\nQ: umbrella, sunscreen, sun hat, sunglasses, cover up, shade\nA: at the beach, name something that might protect you from sun.\nRationale: umbrella, sunscreen, sun hat, sunglasses, cover up and shade can provide protection for the people at the beach\nQ: dog, snake, skunk, frog, mouse\nA:" }, { "from": "gpt", "value": "name an animal that's usually not dangerous, but many people are afraid to touch" } ]

[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you are given a natural language interpretation of commands (consist of logical operations) to select relevant rows from the given table. Your job is to generate command (in terms of logical operations) from given natural language interpretation. Define body (contains a collection of statements that define what the this logical operator does) of each logical operator between '{}' parenthesis. Here are the definitions of logical operators that you can use while generating command: \n 1. count: returns the number of rows in the view. \n 2. only: returns whether there is exactly one row in the view. \n 3. hop: returns the value under the header column of the row. \n 4. and: returns the boolean operation result of two arguments. \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. \n 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. \n 7. argmax/argmin: returns the row with the max/min value in header column. \n 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. \n 9. eq/not_eq: returns if the two arguments are equal. \n 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. \n 11. greater/less: returns if the first argument is greater/less than the second argument. \n 12. diff: returns the difference between two arguments. \n 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. \n 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. \n 15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument. \n 16. filter_all: returns the view itself for the case of describing the whole table \n 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. \n 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. \n 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. \n 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. \n 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. \n 22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.\n\nselect the rows whose partner record fuzzily matches to simon aspelin . the number of such rows is 11 .\n" }, { "from": "gpt", "value": "eq { count { filter_eq { all_rows ; partner ; simon aspelin } } ; 11 }" } ]

[ { "from": "human", "value": "In this task, you are given an article. Your task is to summarize the article in a sentence.\n\nLet me give you an example: Ms Bourne, who became Sussex's first PCC in 2012, was declared winner after the vote went to a second count.\nThree candidates were eliminated in the first count, leaving only Ms Bourne and Labour's Michael Jones.\nIn the first count, Ms Bourne had 114,570 votes and Mr Jones had 61,017. The second count brought their totals to 139,335 and 86,392 respectively.\nShe said: \"I'm absolutely honoured and very privileged to be elected.\"\nShe said she needed to \"find extra savings because budgets are still reducing\" and \"to invest in frontline policing because I know that is really important to people in Sussex\".\nVoter turnout was 22.5% compared with 15.3% in 2012.\nThe three eliminated in the first count were Green Party candidate James Doyle, UKIP's Patrick Lowe and James Walsh from the Liberal Democrats.\nResults listed alphabetically by surname are as follows. BBC News App users: tap here to see the results.\nThe answer to this example can be: Conservative Katy Bourne has been re-elected police and crime commissioner for Sussex.\nHere is why: This is a good example. The output correctly summarizes the article.\n\nOK. solve this:\nDespite losing Terry Campese to injury, Lunt's brace on his return from a calf strain put Rovers 10-0 at half-time.\nKieran Dixon and Ben Cockayne then went in for the visitors before Jamie Jones-Buchanan and Carl Ablett responded.\nFurther tries from Mitch Allgood and Robbie Mulhern ensured Rovers moved above Leeds to 10th in the table.\nVictory is Hull KR's second of the season following James Webster's appointment as interim head coach last month.\nThe defeat is Leeds' third in a row and leaves them second from bottom.\nMedia playback is not supported on this device\nBrian McDermott's treble-winning side looked to have got off to a good start, but Kallum Watkins was adjudged to have knocked on when he went over inside five minutes.\nWhile Danny McGuire gave Leeds an air of surety, Rovers hooker Lunt was clinical for his two first-half scores against his former team.\nDixon ran in from 80 metres to add to Rhinos' woes after the break before Lunt put Cockayne over.\nLeeds' mounted a fightback with the next two tries, but Rovers ran away with it to secure a comfortable victory.\nLeeds Rhinos: Hardaker; Handley, Watkins, Moon, Sutcliffe; McGuire, Burrow; Galloway, Falloon, Cuthbertson, Ablett, Achurch, Jones-Buchanan.\nReplacements: Singleton, Mullally, Walters, Garbutt.\nHull KR: Cockayne; Sio, Horne, Thornley, Dixon; Campese, Marsh; Tilse, Clarkson, Mulhern, Blair, reenwood, Allgood.\nReplacements: Moran, Walker, Green, Lunt.\nAttendance: 15,384\nReferee: Richard Silverwood (RFL)\nAnswer:" }, { "from": "gpt", "value": "Leeds slumped to their seventh defeat in nine games as two Shaun Lunt tries helped fellow Super League strugglers Hull KR beat the defending champions." } ]

[ { "from": "human", "value": "Detailed Instructions: In this task, you are given two statements. The task is to output whether a given textual premise, i.e. Statement 2, entails or implies a given scientific fact, i.e. Statement 1. The output should be 'entails' if Statement 2 supports Statement 1 and should be 'neutral' otherwise.\nProblem:Sentence 1: The number of daylight hours each day would be greatest during the summer near the north pole. Sentence 2: That date will offer every location on earth, except the north and south poles approximately 12 hours of daylight and 12 hours without it.\nSolution:" }, { "from": "gpt", "value": "neutral" } ]

[ { "from": "human", "value": "In this task, you are given an ambiguous question/query (which can be answered in more than one way) and a clarification statement to understand the query more precisely. Your task to classify that if the given clarification accurately clarifies the given query or not and based on that provide 'Yes' or 'No'.\nOne example is below.\nQ: Query: Tell me about defender \n Clarification: are you referring to the arcade game called defender\nA: Yes\nRationale: The given clarification properly clarify the query. Hence, the output is Yes.\nQ: Query: What are the causes of lipoma tumors \n Clarification: are you looking for used car parts from a particular manufacturer\nA:" }, { "from": "gpt", "value": "No" } ]

[ { "from": "human", "value": "Detailed Instructions: Given a command in a limited form of natural language, provide the correct sequence of actions that executes the command to thus navigate an agent in its environment. A command can be broken down into many different actions. Actions are uppercase and are individual steps that serve as the building blocks for a command. For commands, 'left' and 'right' are used to denote the direction of an action. The word 'opposite' turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. Actions and commands do not have quotations in the input and output.\nQ: jump left twice and jump around right\nA:" }, { "from": "gpt", "value": "I_TURN_LEFT I_JUMP I_TURN_LEFT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP" } ]

[ { "from": "human", "value": "In this task, you're given a context passage, a question, and three answer options. Your task is to return an incorrect answer option to the question from the choices given. For all questions, only one of the three answer options is correct. Pick one of the two incorrect answer options as the output.\nQ: Context: Carson turned up the volume in their car so that they could hear the song clearer. \n Question: What does Carson need to do before this? \n Options: (A) go to a bank (B) listen to music (C) buy a cat\nA: " }, { "from": "gpt", "value": "C" } ]

[ { "from": "human", "value": "In this task, you need to count the number of times the given letter appears in the given sentence.\n\nEx Input:\nSentence: 'a red stop sign with street signs above it'. Find frequency of the letter 't'\n\nEx Output:\n5\n\n\nEx Input:\nSentence: 'a man with headphones on is hunched over a sink while being recorded'. Find frequency of the letter 'd'\n\nEx Output:\n4\n\n\nEx Input:\nSentence: 'a herd of giraffe walking across a field'. Find frequency of the letter 'k'\n\nEx Output:\n" }, { "from": "gpt", "value": "1\n\n\n" } ]

[ { "from": "human", "value": "Teacher:In this task, you're given a context passage. Your job is to generate relevant questions that can be answered by directly referring to the passage.\nTeacher: Now, understand the problem? Solve this instance: Last couple of weeks ago , I made sports themed pictures to decorate my nephew and my son's bedroom . I had that idea a while ago , but was too busy to put into action . I went to my sister's house , and my nephew said he wants sports themed wall decoration for his bedroom . He wants baseball and soccer ball pictures .\nStudent:" }, { "from": "gpt", "value": "What's a possible reason I decorated my nephew and my son's bedroom ?" } ]

[ { "from": "human", "value": "Teacher:You will be given a trivia clue, and the category it belongs to. You should answer with the best answer that belongs in the category and is described by the clue. For simplicity, answers should be in all lower cased letters.\nTeacher: Now, understand the problem? Solve this instance: Category: BIBLICAL CITIES \nClue: Of the 10 most populous U.S. cities, the one that shares its name with a city mentioned in Revelation\nStudent:" }, { "from": "gpt", "value": "philadelphia" } ]

[ { "from": "human", "value": "Given a set of four words, generate the category that the words belong to. Words are separated by commas. The possible categories are social gathering, accomodation, physical property, measurement unit, corporate, nutritional value, boats, police punishment, location (proximity), card games, outdoor sport activity, military rank, baby animals, weather, consumer product, animals, boxing terminology, food, chocolate food, bird, type of sandwich, date status, body part, ocean, employment activity, moral characteristic, elements, poker, computers, construction, guitar part, shady activities, physical activity, kitchenware, temperature, type of rigidity, emotional status, season, mode of transportation, window material, activity, emotional display, geographical property, fried food, store status, widespread, aesthetic characteristic, alcoholic drinks, secretary duty, direction, personal characteristic, and animal.\n--------\nQuestion: crane, swift, goose, ostrich\n\nAnswer: bird\n\n\nQuestion: scold, fire, retire, hire\n\nAnswer: employment activity\n\n\nQuestion: whale, sea turtle, fish, dolphin\n\nAnswer:" }, { "from": "gpt", "value": "animal\n\n\n" } ]

[ { "from": "human", "value": "Instructions: In this task, you are given a passage and a question regarding that passage. You must determine whether or not the question is answerable from the given passage. If a question is answerable, output should be 'True', otherwise 'False'. You must not consider any other information that is not provided in the passage while labelling True or False.\nInput: Passage: Connection-oriented transmission requires a setup phase in each involved node before any packet is transferred to establish the parameters of communication. The packets include a connection identifier rather than address information and are negotiated between endpoints so that they are delivered in order and with error checking. Address information is only transferred to each node during the connection set-up phase, when the route to the destination is discovered and an entry is added to the switching table in each network node through which the connection passes. The signaling protocols used allow the application to specify its requirements and discover link parameters. Acceptable values for service parameters may be negotiated. Routing a packet requires the node to look up the connection id in a table. The packet header can be small, as it only needs to contain this code and any information, such as length, timestamp, or sequence number, which is different for different packets. Question: How is error checking involved in delivery? \nOutput:" }, { "from": "gpt", "value": "False" } ]

[ { "from": "human", "value": "Teacher: In this task, you will be given a list of integers. You should remove all of the odd integers from the list(consider 0 an even number). If every integer in the input list is odd then an empty list (\"[]\") should be returned. Otherwise, answer with the list of even numbers separated by comma inside brackets.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\n[1, 8, 0, 2, 9]\nSolution: [8, 0, 2]\nReason: 1 and 9 are removed from the list because they are odd numbers.\n\nNow, solve this instance: [-78, 43, -34, 86, 39, -89, 11, -68, 87]\nStudent:" }, { "from": "gpt", "value": "[-78, -34, 86, -68]" } ]

[ { "from": "human", "value": "In this task, you are given a review of movie. Your task is to classify given movie review into two categories: 1) positive, and 2) negative based on its content.\n\nOne night I was waiting for my friends to come back to the apt and \"Gymkata\" happened to be on; I watched way too much of it. It is indeed hilarious, and horrifying, really. Think about it this way--if in your job you had an idea for something this bad and went on to execute it in as terrible a fashion as this, how long exactly would you last? Not as long as this movie. It's a must-see, obviously." }, { "from": "gpt", "value": "negative" } ]

[ { "from": "human", "value": "Teacher:In this task, you're given an article, a question which often contains a blank and four options (associated with \"A\", \"B\", \"C\", \"D\"). Your task is to find the correct answer (from the given options) for the question from the given article and return one of the options from \"A\", \"B\", \"C\", and \"D\". Do not generate anything else apart from one of the following characters: \"A\", \"B\", \"C\", \"D\". There is only one correct answer for each question.\nTeacher: Now, understand the problem? Solve this instance: Article: In your opinion,what is the most effective way to deal with pressure?Do you think the measure taken by Tufts University is useful? Tufts University has offered extra help around test time to students. Now they're adopting new stress-fighting methods to help the students, who face a tough job market as well as finishing the term. From free massages to therapy dog visits, students are getting help during those days before turning in final papers and taking final exams. \"I think these dogs make me happy and give me a nice break between learning, cutting the learning into small pieces,\"19-year-old Tufts student Chloe Wong said. She called her first term \"challenging\", because she has spent weeks away from family and friends and was afraid she would lose her cool in her first set of final exams. But they now get chances to relax and play with these lovely dogs that head teacher Michael Bliss brought in for them. They can set down their books and laptops for a chance to the pet. Therapy dogs have long been used to cheer the sick and the elderly up. But the university is accepting the idea as a way of relieving stress and comforting students. Brian Van Brunt, president of the American College Counseling Association, said, \"College students are very stressed at this point of the year and some are trying to catch up with their peers. Going to events like this allows students to clear the brain and press there set button.\" \n Question: Which of the following might be the main idea of the passage? \n Options: (A) Therapy dogs help students face difficulties. (B) Therapy dogs make students happy and relaxed. (C) Therapy dogs help students throw pressure away. (D) Therapy dogs help students learn better than before.\nStudent:" }, { "from": "gpt", "value": "C" } ]

[ { "from": "human", "value": "Given the task definition and input, reply with output. You are given a math word problem and you are supposed to make use of mathematical concepts like probability, combinatorics, linear equations, sequences/series, or simple operators like addition, subtraction, division, or multiplication to answer the given question. Choose the best option from the 5 given options and report that option.\n\nQuestion: Find the number of ways in which 7 different beads can be arranged to form a necklace.\n\n Option A: 30\n\n Option B: 20\n\n Option C: 420\n\n Option D: 60\n\n Option E: 80\n" }, { "from": "gpt", "value": "Option C" } ]

[ { "from": "human", "value": "Part 1. Definition\nIn this task, you are given a Reddit post as a text. Your task is to generate a title for this text. The title should start with \"TIFU by\", followed by a situation that caused humor. The title should contain 7-12 words, ideally.\nPart 2. Example\nText: title speaks for itself really... \ni just wasted $1500 of my parents' money.\ni feel terrible.\n\nedit: i guess it wasn't that i took the wrong class, but the class i was taking wouldn't transfer credits over to my university. so really it was my negligence to do more research in the matter. gg\nAnswer: TIFU by taking the wrong class for 2 weeks and only realizing it today\nExplanation: This title is appropriate for the given text post because the focus of this post is about a humorous situation caused by \"taking the wrong class\".\nPart 3. Exercise\nText: names changed (*obviously*)\n\nyesterday i was at an engagement party with my friend elizabeth. we have a lot of friend crossover, so we chat a bit about what is going on in our friends' lives.\n\nabout two years ago, elizabeth had been a bridesmaid at the wedding of mary and joesph. elizabeth told me her friend mary was having an affair. the affair was with joseph's best friend, matt. my friend told me she nearly threw up at the altar, she felt so bad about the entire situation. i had seen mary in passing, i had never met her husband, joseph.\n\nso we're chatting at the party and she mentions that mary is pregnant. i can't quite place a face with the name so i turn to her and say under my breath, \"oh, is she the one who had an affair with matt?\"\n\ni hear this gasp and a \"what?\" behind me. elizabeth turns and i see her face fall. it turns out joseph had been standing within earshot. i had just spilled the beans about his wife's affair, in the middle of a giant party, in front of a whole bunch of our friends. i'm so mortified i stumble over to a trashcan and throw up a whole bunch of luncheon meat.\n\nhe storms over to his wife, they have some words, and then they leave the party so quickly mary doesn't even grab her purse. \n\nso now i feel like a bag of dicks who doesn't know how to shut up and i have no idea how to proceed.\nAnswer:" }, { "from": "gpt", "value": "TIFU by (possibly) destroying a marriage." } ]

[ { "from": "human", "value": "Definition: You will be given one or more triples. The second part of each triple shows the relation between the first and the third element. Your task is to write a simple and short piece of text (sentence(s)) that describes the triples in natural language.\nInput: Alan_Bean | was a crew member of | Apollo_12\nAlan_Bean | dateOfRetirement | \"June 1981\"\nOutput:" }, { "from": "gpt", "value": "Astronaut Alan Bean, who was part of the Apollo 12 crew, retired in June 1981." } ]

[ { "from": "human", "value": "This is a paraphrasing task. In this task, you're given a sentence and your task is to generate another sentence which express same meaning as the input using different words.\n\nare you telling me that i just inhaled an entire loaf of pot banana bread ? !" }, { "from": "gpt", "value": "you want to tell me i got into myself ... a whole piece of bread with pot ? !" } ]

[ { "from": "human", "value": "Given a phrase describing the relationship between two words, extract the words and the lexical relationship between them. The relation has to be of the type 'MemberOf', 'MadeOf', 'Synonym', 'Entails', 'HasA', 'HasProperty', 'PartOf', 'Antonym' or 'IsA'. The output should have the format: word1 relation word2.\n\nmiss can be used as the opposite of see" }, { "from": "gpt", "value": "miss Antonym see" } ]

[ { "from": "human", "value": "In this task, you are given a summary for US Congressional and California state bill, your task is to generate a Title for this bill. The preferred titles are under forty words and mention the purpose of the bill.\nOne example is below.\nQ: Amends the Water Resources Development Act of 1999 to: (1) authorize appropriations for FY 1999 through 2009 for implementation of a long-term resource monitoring program with respect to the Upper Mississippi River Environmental Management Program (currently, such funding is designated for a program for the planning, construction, and evaluation of measures for fish and wildlife habitat rehabilitation and enhancement); (2) authorize the Secretary of the Army to carry out modifications to the navigation project for the Delaware River, Pennsylvania and Delaware, if such project as modified is technically sound, environmentally (currently, economically) acceptable, and economically justified; (3) subject certain previously deauthorized water resources development projects to the seven-year limitation governing project deauthorizations under the Act, with the exception of such a project for Indian River County, Florida; (4) except from a certain schedule of the non-Federal cost of the periodic nourishment of shore protection projects constructed after December 31, 1999, those projects for which a District Engineer's Report has been completed by such date; (5) require that the project cooperation agreement for the Comite River Diversion Project for flood control include a provision that specifies that any reduction in the non-Federal share that results from certain modifications be credited toward the share of project costs to be paid by the Amite River Basin Drainage and Water Conservation District; (6) allow the Secretary to provide additional compensation to Chesapeake City, Maryland (currently, to the City of Chesapeake, Maryland) for damage to its water supply resulting from the Chesapeake and Delaware Canal Project; (7) provide for the submission of certain reports on water resources development projects by the Secretary, notwithstanding Federal reporting termination provisions; and (8) authorize and provide for an authorization of appropriations for the existing program for the safety and operations expenses of the Federal Railroad Administration, and make available for obligation funds currently appropriated for such program.\nA: To make technical corrections to the Water Resources Development Act of 1999.\nRationale: This Bill makes corrections to the Water Resources Development Act of 1999, hence the generated title is correct.\nQ: International Space Station Authorization Act of 1995 - Authorizes appropriations through FY 2002 to the National Aeronautics and Space Administration (NASA) for complete development and initial operations of the International Space Station. Caps appropriations for any one fiscal year. Makes appropriations contingent upon the Administrator of NASA certifying that Space Station budgetary, schedule, and technical commitments will be met. Requires a report to the Congress if such certification cannot be made. \nAuthorizes the Administrator to purchase the Clear Lake Development Facility, containing the Sonny Carter Training Facility, Texas. \nProvides for coordination of the Space Shuttle program with the Space Station Program Office. \nStates that a priority goal of building the International Space Station is the economic development of Earth orbital space. Requires a related commercialization market study. \nExpresses the sense of the Congress that the \"cost incentive fee\" single prime contract for the International Space Station and the consolidation of program management and financial accountability into a single Space Station Program Office should be applied throughout the civil space program. \nRequires the Administrator to submit to the Congress an annual Space Station report, including accounting of all payments to Russia.\nA:" }, { "from": "gpt", "value": "International Space Station Authorization Act of 1995" } ]

[ { "from": "human", "value": "Teacher:In this task, you will be shown a short story with a beginning, two potential middles, and an ending. Your job is to choose the middle statement that makes the story incoherent / implausible by indicating 1 or 2 in the output. If both sentences are plausible, pick the one that makes less sense.\nTeacher: Now, understand the problem? Solve this instance: Beginning: Anna was hiking one day. Middle 1: Anna was able to leap over a small stream in a single bound. Middle 2: Anna was able to leap over a twig in a single bound. Ending: She was thrilled with her daring stunt!\nStudent:" }, { "from": "gpt", "value": "2" } ]

[ { "from": "human", "value": "Instructions: In this task you will be given a list of numbers. A list is shown by two brackets and comma-separated numbers inside, like: [1,2,3]. You should remove all of the even numbers from the list. If every number in the input list is even an empty list should be returned. Zero should be counted as an even number.\nInput: [46, 40, 176, 156, 61, 123, 79]\nOutput:" }, { "from": "gpt", "value": "[61, 123, 79]" } ]

[ { "from": "human", "value": "In this task, you are given a text from tweets. Your task is to classify given tweet text into two categories: 1) positive, and 2) negative based on its content.\nOne example is below.\nQ: @justinchuan Awww! I was thinking about you lot up there! Glad you enjoyed it\nA: positive\nRationale: There is an expression of happiness in this tweet text, hence we can say it's positive.\nQ: @rainbowchasing oops!? *lol* Sorry I kind of spam your profile with my updates Hopefully you won't remove me from your follower list.\nA:" }, { "from": "gpt", "value": "negative" } ]

[ { "from": "human", "value": "A ploynomial equation is a sum of terms. Here each term is either a constant number, or consists of the variable x raised to a certain power and multiplied by a number. These numbers are called weights. For example, in the polynomial: 2x^2+3x+4, the weights are: 2,3,4. You can present a polynomial with the list of its weights, for example, equation weights = [6, 4] represent the equation 6x + 4 and equation weights = [1, 3, 4] represent the equation 1x^2 + 3x + 4. In this task, you need to compute the result of a polynomial expression by substituing a given value of x in the given polynomial equation. Equation weights are given as a list.\n--------\nQuestion: x = 6, equation weights = [2, 4]\n\nAnswer: 16\n\n\nQuestion: x = 4, equation weights = [0, 5]\n\nAnswer: 5\n\n\nQuestion: x = 8, equation weights = [2, 4]\n\nAnswer:" }, { "from": "gpt", "value": "20\n\n\n" } ]

[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given a fact statement and question based on the fact. Your task is to generate the correct answer for the question. The answer needs to be generated using the context fact statement.\n\nFact: when the body is hot , sweat is produced to cool the body. Question: If one was to cease perspiration, what would they be most at risk for?\nOutput:" }, { "from": "gpt", "value": "overheating" } ]

[ { "from": "human", "value": "In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\n\n15, 16, ['7679', '111', 'M', 'G', 'G', 'L', 'J', 't', 'U', '4913', 'J', 'u', 'i', 'U', '2225', 'W', '2151', '5665', 'g', 'X', '607', 'v', '6665', '101', '3549', 'f', '9487']" }, { "from": "gpt", "value": "2225, W" } ]

[ { "from": "human", "value": "Q: In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\n19, 21, ['H', '5185', '6437', 'F', '8171', 'g', 's', 'W', 'l', '1523', '6139', 'T', '8485', '5221', 'j', '1689', 'n', '6161', '6949', '2581', 'G', '1349', 'V']\nA:" }, { "from": "gpt", "value": "6949, 2581, G" } ]

[ { "from": "human", "value": "In this task you are given a medical question pair hand-generated. Your task is to classify a given post into two categories 1) 'Similar' if the given two questions have a same connotation 2) 'Dissimilar' if the given two questions have a different connotation or meaning.\n\nSentence1: I'm 16 weeks pregnant and the skin on left side of my stomach and back is sensitive and extremely painful when touched. But I have no rash. Why? \n Sentence2: My wife is 16 weeks pregnant, she had a fall and now her left side of stoamch and back is very painful. What should I do? \nDissimilar\n\nSentence1: My boyfriend has been experiencing shortness of breathe for the past week, he went to the doctor they checked all his vital signs and his oxygen level and everything came back a okay, do you have any idea what the problem may be ? Please help i'm really w \n Sentence2: My boy friend has shortness of breath since past week and all his vital signs are normal. I am concerned as what to do. \nSimilar\n\nSentence1: What is the definition or description of: activity modification? \n Sentence2: What are some exercises and changes to lifestyle that I can do? I'm not sure but the doctor has advised me \"activity modification\". What does it mean?\n" }, { "from": "gpt", "value": "Similar\n\n" } ]

[ { "from": "human", "value": "Read the given query and classify it as a 'Good' or 'Bad' query depending on how well the query is formed, 'Bad' being the expected output for a not so well formed query and 'Good' being the expected output for a well formed query. A query may be wrong based on common sense or general facts, but if it is well formed, you should answer with Good.\n\nExample Input: What is the sodium-ptassium pump ?\nExample Output: Bad\n\nExample Input: How can break power password on laptop ?\nExample Output: Bad\n\nExample Input: What year did tv go color ?\nExample Output:" }, { "from": "gpt", "value": "Good\n\n" } ]

[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given a premise sentence. Your task is to write a new sentence by substituting the subject and object (i.e., the input's subject should be output's object and vice versa.). The generated sentence must be fluent and shouldn't change the voice (i.e., passive or active) of the input.\n\nThe secretary called the manager .\nOutput:" }, { "from": "gpt", "value": "The manager called the secretary ." } ]

[ { "from": "human", "value": "Teacher: In this task, you are given a fact statement and question based on the fact. Your task is to generate the correct answer for the question. The answer needs to be generated using the context fact statement.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nFact: deep sea animals live deep in the ocean. Question: Frilled sharks and angler fish live far beneath the surface of the ocean, which is why they are known as?\nSolution: Deep sea animals\nReason: This is the correct answer since the fact says that deep sea animals live deep in the ocean and the question asks for what fish who live deep in the ocean are called.\n\nNow, solve this instance: Fact: when the body is hot , sweat is produced to cool the body. Question: If one was to cease perspiration, what would they be most at risk for?\nStudent:" }, { "from": "gpt", "value": "overheating" } ]

[ { "from": "human", "value": "In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to choose whether the two sentences clearly agree (entailment)/disagree (contradiction) with each other, or if this cannot be determined (neutral). Your answer must be in the form of the letters E, C, and N respectively.\nQ: Sentence 1: People and goats are walking around a muddy field. Sentence 2: a people with some goats in a field\nA: " }, { "from": "gpt", "value": "C" } ]

[ { "from": "human", "value": "Instructions: Craft one incorrect answer. In doing so, try to use words from the context as much as possible, or by using similar words used in the correct answer. DO NOT craft nonsensical or off-topic incorrect answers, such that the incorrect answers can be directly excluded without reasoning according to the context. Try to make your responses similar to the given correct answer. To this end, try to keep both the length and the style as similar as possible between the correct and the incorrect answer. To make your incorrect answers more difficult, try to incorporate words from context. To avoid being predictable or repetitive, try to add more variations and complexity.\nInput: Context: They really were stunningly similar , with a spattering of freckles and a puff of pale hair on their heads . If it was n't for the cut and the expressions on their faces , she would n't have been able to tell them apart . She stood back up . \nQuestion: Why are the two individuals hard to tell apart ? \nCorrect Answer: The two individuals share similar traits such as freckles and pail hair .\nOutput:" }, { "from": "gpt", "value": "The two individuals are not really doppelgangers ,." } ]

[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIf the emotion of happiness is present in the one of the dialogues of the conversation, then output Yes otherwise output No\n\nI think this spring is a good time for us to start looking . We should plan to move out of here before July . I'm tired of living in apartments . I know , dear . I am too . But we've just been too busy to look for a house . We need to find a good realtor . Not necessary . If we use a realtor to find a house , it will be more expensive . What do you mean ? Realtors always get a commission . If the realtor helps us find something , we have to pay him . But doesn't a realtor help with the contract ? I thought they take care of all the legal troubles . Yes , that's often true . But you have to pay them . I still think we should have a realtor . We're new in this country . We don't know all the laws of buying a house . And also , the realtor will inspect the house . He can tell us if the house has any problems . Of course we need a house inspector . But we can hire an inspector on our own . As for the legal problems , I have friends . They can help us . So how can we find a house if we don't have a realtor ? It takes a little more time . We have to check the ads in the paper . Probably also there are special real estate magazines with ads . Then we have to drive to the homes and look at them . And doesn't the person selling the house have a realtor ? Sometimes they do , sometimes they don't . It's best to find someone who is selling by themselves . Why ? That is because if the seller has a realtor , their price will be higher . He will have to pay a commission to the realtor . Hmm . It all sounds very complicated . It is . But buying a house is very important . So it takes time . That's why we haven't done it yet . It's very troublesome . I want to look in the papers today . Maybe we can see something we like . All right . I'll buy a newspaper when I go to the drugstore . \nOutput:" }, { "from": "gpt", "value": "No" } ]

[ { "from": "human", "value": "In this task your given two statements in Indonesian. You must judge whether the second sentence is the cause or effect of the first one. Label the instances as \"cause\" or \"effect\" based on your judgment. The sentences are separated by a newline character.\n\nInput: Consider Input: Saya tolak undangan pesta ulang tahun itu.\nSaya sedang di luar kota.\n\nOutput: cause\n\n\nInput: Consider Input: Pria itu memenangkan lotre.\nIa menjadi kaya.\n\nOutput: effect\n\n\nInput: Consider Input: Saya rapihkan rumah saya.\nSaya mengharapkan ada yang menemani saya.\n\n" }, { "from": "gpt", "value": "Output: cause\n\n\n" } ]

[ { "from": "human", "value": "Given the sentence, generate \"yes, and\" response. \"Yes, and\" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated (\"Yes\") and then expand on that line of thought or context (\"and...\"). 1 In short, a \"Yes, and\" is a dialogue exchange in which a speaker responds by adding new information on top of the information/setting that was constructed by another speaker. Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange, although it could be the case if it agrees with the description above. There are many ways in which a response could implicitly/explicitly agree to the prompt without specifically saying 'yes, and...'. \n\nInput: Consider Input: We both sleep on the top bunk because the bottom bunk is too dangerous.\n\nOutput: It's too dangerous! That's where people get strangulated!\n\n\nInput: Consider Input: Bartal, if I don't hear this little new shit, Mindy sing within the next 30 seconds, I am going to explode. You better get her singing.\n\nOutput: I will. Welcome aboard, Miss Cynthia. It's great to have you finally be southern.\n\n\nInput: Consider Input: What is wrong with you, mysterious guy? Why do you have Scruples and six yo-yo's in your jacket?\n\n" }, { "from": "gpt", "value": "Output: I just want to read Scruples and practice my yo-yo'ing with different weights of yo-yo.\n\n\n" } ]

[ { "from": "human", "value": "Given the task definition and input, reply with output. You are given two sentences. You have to find if there is entailment or agreement of the Hypothesis by the Premise. From the given pair of sentences, you should identify if there is enough information in the Premise to support the claim made in the Hypothesis. The Premise may not exactly be the same as Hypothesis. Your task is to return 'entails' if the premise supports hypothesis else return 'neutral'.\n\nPremise: Most of the energy that is used by living organisms on earth ultimately comes from the sun in the form of radiant energy . \n Hypothesis: Most of the energy used by living things comes either directly or indirectly from the sun.\n" }, { "from": "gpt", "value": "entails" } ]

[ { "from": "human", "value": "TASK DEFINITION: In this task, you are given product reviews about dvds. The goal is to classify the review as \"POS\" if the overall sentiment of the review is positive(the reviewer is satisfied) or as \"NEG\" if the overall sentiment of the review is negative(the reviewer is not satisfied).\nPROBLEM: Very Nude but not very Yoga . I can't judge the Tai Chi but the Yoga in this video was not well done. The producers hired attractive women with gorgeous bodies and large breasts--but no Yoga skills. So this video does not combine the beauty of Yoga with the beauty of the human body. It would be absolutely wonderful to have a talented and flexible Yoga instructor do Yoga postures correctly...and in a manner that is intentionally sexually explicit and erotic. I don't see any problem with that. Probably few if any dedicated Yoga instructors would consider doing that sort of video. I'm sure it would be frowned upon by the serious Yoga community which might consider it degrading. So we end up with a second rate product like this video. Too bad. Nevertheless, I do enjoy watching these women show us their bodies\n\nSOLUTION: NEG\n\nPROBLEM: Just Say No, Cuz! . This movie provides ample proof that LSD usage does affect the minds of the unborn. Grateful Dead legend Jerry Garcia's daughter made this amateurish home video. While the topic of genetically modified foods is interesting, this video comes off as terribly one-sided hatchet job on the biotech industry and U.S. agriculture, in general. Monsanto is the main target of this film's attacks, but no one from the company is ever allowed to respond to the claims that it is trying to monopolize the pesticide and seed industries by buying up potential competitors and registering for patents on thousands of genetically engineered plant products. Instead, we're treated to the overzealous opinions of a few blowhards who don't have any idea of how to encourage research, development, and innovation in agriculture. The vague term of \"biodiversity\" is mentioned as some kind of virtue, but no explains its benefits. Actually, everyone is allowed to whine in this movie, from farmers to activists, but no one is ever allowed to respond to attacks. In one sequence, a farmer criticizes Monsanto. In another sequence, the U.S. government is criticized for subsidizing farmers (nevermind that every major industrial power subsidizes its farmers). Why not ask the farmer if he's dependent on government handouts, and how he justifies such subsidies? Why should farmers be immune to criticism? Please, let's get into the mix a little bit, and get to the bottom of these controveries!\n\nSOLUTION: NEG\n\nPROBLEM: Eight Men Out . The film is fantastic for all baseball lovers, history lovers, and anyone who wishes to escape for a few hours. No baseball fan should miss this one\n\nSOLUTION:" }, { "from": "gpt", "value": "POS\n\n" } ]

[ { "from": "human", "value": "Teacher: Craft one incorrect answer. In doing so, try to use words from the context as much as possible, or by using similar words used in the correct answer. DO NOT craft nonsensical or off-topic incorrect answers, such that the incorrect answers can be directly excluded without reasoning according to the context. Try to make your responses similar to the given correct answer. To this end, try to keep both the length and the style as similar as possible between the correct and the incorrect answer. To make your incorrect answers more difficult, try to incorporate words from context. To avoid being predictable or repetitive, try to add more variations and complexity.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nContext: I was told, in person over the phone, that my shoes were on their way. They have my money. I have no shoes. \nQuestion: What may happen before I called them? \nCorrect answer: I found the money was charged but I have not got shoes.\nSolution: I found the shoes were still on the way after several days.\nReason: Excellent incorrect answer: as it includes topically relevant words while still being incorrect.\n\nNow, solve this instance: Context: They really were stunningly similar , with a spattering of freckles and a puff of pale hair on their heads . If it was n't for the cut and the expressions on their faces , she would n't have been able to tell them apart . She stood back up . \nQuestion: Why are the two individuals hard to tell apart ? \nCorrect Answer: The two individuals share similar traits such as freckles and pail hair .\nStudent:" }, { "from": "gpt", "value": "The two individuals are not really doppelgangers ,." } ]

[ { "from": "human", "value": "Detailed Instructions: In this task, you are given an input list A comprising of numbers and alphabets. You need to extract and sort the unique alphabets in the list. The alphabets in the input list will only be in lowercase. Return -1 if there is no alphabet in the input list.\nProblem:['k', '3171', 'i', '6951', 'j', '7467', 'q', 'z', '4121', 'z', '2853', '3927', '6259', 't', 'x', 'h', 'e', '1803', '9767', '2275', 'h', 't', 'a', '9251', 'j', 'o', '5111', 't', '7725', 'f', 'c', 'q', '7819', '8889', '6309', '9981', '7765', 'y']\nSolution:" }, { "from": "gpt", "value": "a, c, e, f, h, i, j, k, o, q, t, x, y, z" } ]

[ { "from": "human", "value": "In this task, you are given a review of movie. Your task is to classify given movie review into two categories: 1) positive, and 2) negative based on its content.\n\nInput: Consider Input: As someone who lived through,and still remembers that decade vividly,if the actual '70s had been half this funny and (semi)normal,they would have been so much more enjoyable.Actual kids in that era did not act or behave anything close to as bright-eyed and normal as these kids did.The country's youth was still under the influence of the hippies and the drug culture all that '60s rebellion that it spawned,especially in the behavior department;the petulance,the smugness,the self-righteousness,the childishness,the unreasonableness of them - none of the characters exhibit any of that.Someone compared to \"Happy Days\",and I can see why:They were both sitcoms that take place 20 years before the current time they were broadcast,and they both offer only surface ,cliched depictions of the actual eras,not even close to the full scope of it,just showing the obvious things - the fashions,toys,music,contraptions,etc,and that's it.For those too young to remember,or weren't born then,trust me,the '70s weren't like that,any more than \"Happy Days\" were like the actual '50s,as \"M*A*S*H*\" didn't accurately portray life at a US Army medical base during the Korean War,etc.\n\nOutput: negative\n\n\nInput: Consider Input: In what is arguably the best outdoor adventure film of all time, four city guys confront nature's wrath, in a story of survival. The setting is backwoods Georgia, with its forests, mountains, and wild rivers.The director, John Boorman, chose to use local people, not actors, to portray secondary characters. These locals imbue the film with a depth of characterization unequaled in film history. No central casting \"actors\" could ever come close to these people's remarkable faces, voices, or actions. I don't recall a film wherein the secondary characters are so realistic and colorful. As much as anything else, it is this gritty realism that makes this film so amazing.Another strength is the film's theme. Nature, in the wild, can be violent. How appropriate that the setting should be the American South. Very few places in the U.S. are, or have been, as violent as redneck country. In a story about Darwinian survival of the fittest, the film conveys the idea that humans are part of nature, not separate from it.\"Deliverance\" is very much a product of its time when, unlike today, Americans expressed concern over a vanishing wilderness. The film's magnificent scenery, the sounds of birds, frogs, crickets, and the roar of the river rapids, combined with the absence of civilization, all convey an environmental message. And that is another strength of the film.At an entertainment level, the tension gradually escalates, as the plot proceeds. Not even half way into the film the tension becomes extreme, and then never lets up, not until the final credits roll. Very few films can sustain that level of intensity over such a long span of plot.Finally, the film's technical quality is topnotch. Direction and editing are flawless. Cinematography is excellent. Dialogue is interesting. And the acting is terrific. Burt Reynolds has never been better. Ned Beatty is perfectly cast and does a fine job. And Jon Voight should have been nominated for an Oscar. If there is a weak link in the film, it is the music, which strikes me as timid.Overall, \"Deliverance\" almost certainly will appeal to viewers who like outdoor adventure. Even for those who don't, the gritty characterizations, the acting, and the plot tension are reasons enough to watch this film, one of the finest in cinema history.\n\nOutput: positive\n\n\nInput: Consider Input: Except for the Brady Variety Hour, this was some of the hokiest television I've seen in a while. The video production qualities weren't too bad, but the overall look and feel were unmistakeably early 80's. And Marie Osmond looks like she did battle with the Avon Lady.. and lost big time. WAY too much eyeliner.It was kind of embarrassing to watch veterans Danny Kaye and Eric Severeid take part in this. Even more interesting was watching Alex Haley talk about the African Pavillion in World Showcase that would be opening 'in about a year.'As of this writing it is 17 years later and it hasn't opened yet (Unless you count Disney's Animal Kingdom.) All in all though, for all the shortcomings, this still an interesting visual piece of Disney history.\n\n" }, { "from": "gpt", "value": "Output: negative\n\n\n" } ]

[ { "from": "human", "value": "Read the passage and find the corresponding person for the given pronoun. The word between ** ** is the target pronoun.\nQ: On March 21, 2006, Murray was fired by the Kings and was replaced on an interim basis by John Torchetti. He provided colour commentary for the Canadian Broadcasting Corporation during their Hockey Night in Canada telecasts of the 2006 Stanley Cup playoffs. On December 11, 2006, the Blues hired Murray to replace Mike Kitchen as head coach after a seven game losing streak. **He** coached the Blues to a record of 33--36--13 in his first full season as coach in 2007--2008.\nA: " }, { "from": "gpt", "value": "Murray" } ]

[ { "from": "human", "value": "Teacher: In this task, you are given an answer, and your task is to generate a reasonable question for that answer.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nMy stomach will be upset if i eat that.\nSolution: Do you like pineapple on your pizza?\nReason: The answer given was regarding something that the person ate and it caused his stomach upset. The question asked was if that person likes pineapple on pizza. Based on the given answer, the question was predicted correctly.\n\nNow, solve this instance: I was born outside the country.\nStudent:" }, { "from": "gpt", "value": "Were you born in town?" } ]

[ { "from": "human", "value": "Teacher: In this task, you are given an abstract of article. Your task is to generate title for this article. Preferred titles are under thirty words.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nAlterations of the architecture of cerebral white matter in the developing human brain can affect cortical development and result in functional disabilities. A line scan diffusion-weighted magnetic resonance imaging (MRI) sequence with diffusion tensor analysis was applied to measure the apparent diffusion coefficient, to calculate relative anisotropy, and to delineate three-dimensional fiber architecture in cerebral white matter in preterm (n = 17) and full-term infants (n = 7). To assess effects of prematurity on cerebral white matter development, early gestation preterm infants (n = 10) were studied a second time at term. In the central white matter the mean apparent diffusion coefficient at 28 wk was high, 1.8 microm2/ms, and decreased toward term to 1.2 microm2/ms. In the posterior limb of the internal capsule, the mean apparent diffusion coefficients at both times were similar (1.2 versus 1.1 microm2/ms). Relative anisotropy was higher the closer birth was to term with greater absolute values in the internal capsule than in the central white matter. Preterm infants at term showed higher mean diffusion coefficients in the central white matter (1.4 +/- 0.24 versus 1.15 +/- 0.09 microm2/ms, p = 0.016) and lower relative anisotropy in both areas compared with full-term infants (white matter, 10.9 +/- 0.6 versus 22.9 +/- 3.0%, p = 0.001; internal capsule, 24.0 +/- 4.44 versus 33.1 +/- 0.6% p = 0.006). Nonmyelinated fibers in the corpus callosum were visible by diffusion tensor MRI as early as 28 wk; full-term and preterm infants at term showed marked differences in white matter fiber organization. The data indicate that quantitative assessment of water diffusion by diffusion tensor MRI provides insight into microstructural development in cerebral white matter in living infants.\nSolution: Microstructural development of human newborn cerebral white matter assessed in vivo by diffusion tensor magnetic resonance imaging.\nReason: This title is appropriate for the given abstract because the focus of this abstract is cerebral white matter assesment.\n\nNow, solve this instance: The melanocortin receptor 4 (MC4R) is a well-established mediator of body weight homeostasis. However, the neurotransmitter(s) that mediate MC4R function remain largely unknown; as a result, little is known about the second-order neurons of the MC4R neural pathway. Single-minded 1 (Sim1)-expressing brain regions, which include the paraventricular nucleus of hypothalamus (PVH), represent key brain sites that mediate melanocortin action. We conditionally restored MC4R expression in Sim1 neurons in the background of Mc4r-null mice. The restoration dramatically reduced obesity in Mc4r-null mice. The anti-obesity effect was completely reversed by selective disruption of glutamate release from those same Sim1 neurons. The reversal was caused by lower energy expenditure and hyperphagia. Corroboratively, selective disruption of glutamate release from adult PVH neurons led to rapid obesity development via reduced energy expenditure and hyperphagia. Thus, this study establishes glutamate as the primary neurotransmitter that mediates MC4Rs on Sim1 neurons in body weight regulation.\nStudent:" }, { "from": "gpt", "value": "Glutamate mediates the function of melanocortin receptor 4 on Sim1 neurons in body weight regulation." } ]

[ { "from": "human", "value": "In this task you are given a sentence pair from wikipedia that have high lexical overlap. If the sentences have the same meaning and are just paraphrases of each other label them as \"Paraphrase\" , if not label them as \"Not paraphrase\". The two sentences are seperated by a new line.\nOne example is below.\nQ: In January 2011 , the Deputy Secretary General of FIBA Asia , Hagop Khajirian , inspected the venue together with SBP - President Manuel V. Pangilinan .\nIn January 2011 , FIBA Asia deputy secretary general Hagop Khajirian along with SBP president Manuel V. Pangilinan inspected the venue .\nA: Paraphrase\nRationale: The second sentence has the same meaning as the first sentence and is just a paraphrased version of it.\nQ: John is survived by his daughter and his son Annabel and Richard Ogdon .\nJohn is survived by his daughter and son , Annabel and Richard Ogdon .\nA:" }, { "from": "gpt", "value": "Paraphrase" } ]

[ { "from": "human", "value": "instruction:\nGiven an trivia question precisely answer the question with a word/phrase/name. External resources such as Wikipedia could be used to obtain the facts.\nquestion:\nBased in Mumbai, abbreviated to RBI, what is India's central banking institution and guardian of the currency?\nanswer:\nreserve bank of india\n\n\nquestion:\nWho painted The Haywain?\nanswer:\njohn constable\n\n\nquestion:\nWhich 2013 film tells the story of Martin Sixsmith's attempts to re-unite an Irish mother with her son, taken away by nuns after his birth?\nanswer:\n" }, { "from": "gpt", "value": "philomena\n\n\n" } ]

[ { "from": "human", "value": "Detailed Instructions: In this task, you are given an input list A. You need to find all the elements of the list that are numbers in the same order as they appear in the list A.\nProblem:['81', 'u', 'N', '8727', 'J', '3981', 'F', 'z', '7313', 'b', '1501', '2769', '2089', '8493', '4835', 'r', 'n', '2177', '4725', '5163', 'z']\nSolution:" }, { "from": "gpt", "value": "81, 8727, 3981, 7313, 1501, 2769, 2089, 8493, 4835, 2177, 4725, 5163" } ]

[ { "from": "human", "value": "The input is a sentence. The sentence includes an emotion. The goal of the task is to classify the emotion in the sentence to one of the classes: 'fear', 'joy', 'anger', 'sadness'. The emotion mainly depends on the adverb within the sentence.\n\nEx Input:\nEbony made me feel sad.\n\nEx Output:\nsadness\n\n\nEx Input:\nRoger feels discouraged.\n\nEx Output:\nfear\n\n\nEx Input:\nMalik feels scared.\n\nEx Output:\n" }, { "from": "gpt", "value": "fear\n\n\n" } ]

[ { "from": "human", "value": "Q: You are given a question. You need to detect which category better describes the question. A question belongs to the description category if it asks about description and abstract concepts. Entity questions are about entities such as animals, colors, sports, etc. Abbreviation questions ask about abbreviations and expressions abbreviated. Questions regarding human beings, description of a person, and a group or organization of persons are categorized as Human. Quantity questions are asking about numeric values and Location questions ask about locations, cities, and countries. Answer with \"Description\", \"Entity\", \"Abbreviation\", \"Person\", \"Quantity\", and \"Location\".\nWhat prison is found in Ossining , New York ?\nA:" }, { "from": "gpt", "value": "Location" } ]

[ { "from": "human", "value": "In this task, you're given a statement and three sentences as choices. Your job is to determine the neutral choice based on your inference from the statement and your commonsense knowledge. The neutral choice is a sentence that neither agrees nor disagrees with the statement. Indicate your answer as '1', '2', or '3', corresponding to the choice number of the selected sentence. If sentence X agrees with sentence Y, one's correctness follows from the other one. If sentence X disagrees with sentence Y, they can not be correct at the same time.\n\nExample Input: Statement: Most articles remain in the current contents list for a week. Choices: 1. The current contents lists most articles. 2. The current contents also list the page numbers. 3. The articles do not remain anywhere. \nExample Output: 2\n\nExample Input: Statement: That gentleman nodded approval. Choices: 1. The man nodded a yes. 2. The man never nodded. 3. The man nodded and waved.\nExample Output: 3\n\nExample Input: Statement: the interesting thing about it is is that from a uh uh an economy standpoint or in economics i i thinks it's i think it's poor poor uh economics to to carry all that consumer debt at least from a tax standpoint so Choices: 1. I don't think the consumer debt is placed upon poor economics. 2. I think it's unfortunate where the consumer debt ends up. 3. From a tax standpoint, I think poor economics carries the consumer debt.\nExample Output:" }, { "from": "gpt", "value": "2\n\n" } ]

[ { "from": "human", "value": "Teacher: You are given a dialog between 2 or more individuals. Within the dialog, there will be clues that indicate two individuals were or are dating. You will be prompted at the end to answer which Speaker (or named individual) is dating which other Speaker (or named individual).\nTeacher: Now, understand the problem? If you are still confused, see the following example:\n'Speaker 1: Hi! \nSpeaker 2: Hi. \nSpeaker 1: Oh, I'm so glad you called. I feel like it's always me calling you. So, what's up? Is everything okay with Phoebe? \nSpeaker 2: It will be...in a minute. Listen, Tim you're a really great guy. \nSpeaker 1: It's because I'm with you. \nSpeaker 2: Aw. I'm just-I'm in a place in my life right now where I...I... \nSpeaker 1: Whoops. Sorry. This just in. Oh, it's 9-1-1 from the restaurant, that means Monica needs me right away.\nSpeaker 2: Oh-oh no she doesn't! I know what that is. You can stay. \nSpeaker 1: Awww, I'll miss you too Pheebs. And I will be holding you, right here. \nSpeaker 2 is or was dating which Speaker?'\nSolution: Speaker 1\nReason: Speaker 2 is giving clues to Speaker 1 about issues in their relationship.\n\nNow, solve this instance: Speaker 1: And why not?! \nSpeaker 2: Because I'm in love with Monica!! \nSpeaker 1: You're-you're what?! \nSpeaker 2: Love her! That's right, I...LOVE...HER!!! I love her!! I love you, Monica. \nSpeaker 3: I love you too Chandler. \nSpeaker 1: I just-I thought you guys were doing it, I didn't know you were in love! \nSpeaker 4: Dude! \nSpeaker 2: And hats off to Phoebe. Quite a competitor. And might I say your breasts are still showing. \nSpeaker 1: God! \nSpeaker 4: All right! So that's it! It's over! Everybody knows! \nSpeaker 3: Well actually, Ross doesn't. \nSpeaker 2: Yes, and we'd appreciate it if no one told him yet. Speaker 2 is or was dating which Speaker?\nStudent:" }, { "from": "gpt", "value": "Speaker 3" } ]

[ { "from": "human", "value": "In this task, you are given a short story consisting of exactly 5 sentences where the second sentence is missing. You are given two options and you need to select the one that best connects the first sentence with the rest of the story. Indicate your answer by 'Option 1' if the first option is correct, otherwise 'Option 2'. The incorrect option will change the subsequent storyline, so that at least one of the three subsequent sentences is no longer consistent with the story.\n\nSentence 1: I love to eat potato chips. \n Sentence 3: When I was eating I noticed a competition entry on the bag \n Sentence 4: It asks you to submit your flavor for a chance to win \n Sentence 5: I'm still waiting for my cheeto flavor idea \n Option 1: One day I was eating potato chips out of a bowl. \n Option 2: One day I was eating potato chips out of a bag." }, { "from": "gpt", "value": "Option 2" } ]

[ { "from": "human", "value": "Teacher: In this task, you are given two lists A,B. Find the longest common subsequence in the lists A and B.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\n[5797, 8817, '8297', 'b', 'U', 'b'], [5843, 8809, '8297', 'b', 'W', 'C']\nSolution: 8297, b\nReason: Here, '8297, b' is the longest common subsequence in both the input lists [5797, 8817, '8297', 'b', 'U', 'b'] and [5843, 8809, '8297', 'b', 'W', 'C'].\n\nNow, solve this instance: ['D', 5643, 'e', 'C', 'd', '8373', '9341', '3233', '8371', 'C', '9603', 'D', 'V', 'E', 749, 'y', 7205], [9477, 'j', 8109, '8373', '9341', '3233', '8371', 'C', '9603', 'D', 'V', 'f', 'A', 'y', 'W', 'u', 'K', 2385, 2753]\nStudent:" }, { "from": "gpt", "value": "8373, 9341, 3233, 8371, C, 9603, D, V" } ]

[ { "from": "human", "value": "Detailed Instructions: Categorize the comment on the basis of threat. If the comment is threatening output Yes, otherwise output No.\nProblem:Totally agree. In what little I heard of his talk on video, he just talked about himself and how great he is. It's like he commissioned a study to see what the 3 most hot-button issues are that will bring people to the poles and focuses on them. He lacks even the tiniest bit of sincerity or humility. His \"I love women\" and \"I love Hispanics\" couldn't be more insincere and shallow, nor could his ideas on running the country.\nSolution:" }, { "from": "gpt", "value": "No" } ]

[ { "from": "human", "value": "You are given a question. You need to detect which category better describes the question. A question belongs to the description category if it asks about description and abstract concepts. Entity questions are about entities such as animals, colors, sports, etc. Abbreviation questions ask about abbreviations and expressions abbreviated. Questions regarding human beings, description of a person, and a group or organization of persons are categorized as Human. Quantity questions are asking about numeric values and Location questions ask about locations, cities, and countries. Answer with \"Description\", \"Entity\", \"Abbreviation\", \"Person\", \"Quantity\", and \"Location\".\n--------\nQuestion: What are a baseball team 's firemen ?\n\nAnswer: Description\n\n\nQuestion: Where does your hair grow the fastest ?\n\nAnswer: Entity\n\n\nQuestion: How can SQL queries be improved ?\n\nAnswer:" }, { "from": "gpt", "value": "Description\n\n\n" } ]

[ { "from": "human", "value": "You will be given two questions. You should decide whether the second question is a good paraphrase of the first one. If you are able to tell that the two questions are the same without any other information, answer \"Yes\", otherwise answer \"No\".\n\noriginal question: Find opera productions whose stage director is [Arno Wuestenhoefer].\nparaphrase: SEARCH OPERA PRODUCTIONS WHERE [Arno Wuestenhoefer] BE THE SCENE DIRECTOR.\nNo\n\noriginal question: Which geographical scope belongs to the conference series which is the subject of [Religion]?\nparaphrase: [Religion] belongs to what geographical scope?\nNo\n\noriginal question: What adaptation is adapted from [Via Mala]\nparaphrase: What novel by the Swiss writer John Knittel is an adaptation of [Via Mala]?\n" }, { "from": "gpt", "value": "Yes\n\n" } ]

[ { "from": "human", "value": "Detailed Instructions: In this task, you will be presented with a question about part-of-speech tag of a word in the question. You should write an implausible POS tag to the question. Even though there exist multiple wrong answers, we only need a single wrong answer. Here is the Alphabetical list of part-of-speech tags used in this task: CC: Coordinating conjunction, CD: Cardinal number, DT: Determiner, EX: Existential there, FW: Foreign word, IN: Preposition or subordinating conjunction, JJ: Adjective, JJR: Adjective, comparative, JJS: Adjective, superlative, LS: List item marker, MD: Modal, NN: Noun, singular or mass, NNS: Noun, plural, NNP: Proper noun, singular, NNPS: Proper noun, plural, PDT: Predeterminer, POS: Possessive ending, PRP: Personal pronoun, PRP$: Possessive pronoun, RB: Adverb, RBR: Adverb, comparative, RBS: Adverb, superlative, RP: Particle, SYM: Symbol, TO: to, UH: Interjection, VB: Verb, base form, VBD: Verb, past tense, VBG: Verb, gerund or present participle, VBN: Verb, past participle, VBP: Verb, non-3rd person singular present, VBZ: Verb, 3rd person singular present, WDT: Wh-determiner, WP: Wh-pronoun, WP$: Possessive wh-pronoun, WRB: Wh-adverb\nProblem:What is the part-of-speech tag of the word \"Mountains\" in the following question: Which original chapter has washington and lee university together and lies between the Atlantic Coast and the Appalachian Mountains ?\nSolution:" }, { "from": "gpt", "value": "RB" } ]

[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you need to answer the given multiple-choice question on the general math. Classify your answers into 'a', 'b', 'c', 'd', and 'e'.\nExample: Problem: what is difference between biggest and smallest fraction among 2 / 3 , 3 / 4 , 4 / 5 and 5 / 3 \nOptions: a ) 2 / 5 , b ) 3 / 5 , c ) 1 / 6 , d ) 1 , e ) none of these\nOutput: d\n\"explanation : 2 / 3 = . 66 , 3 / 4 = . 75 , 4 / 5 = . 8 and 5 / 3 = 1.66 so the biggest is 5 / 3 and the smallest is 2 / 3 their difference is 5 / 3 - 2 / 3 = 3 / 3 = 1 option d\"\n\nNew input case for you: Problem: drum x is 1 / 2 full of oil and drum y , which has twice the capacity of drum x , is 2 / 5 full of oil . if all of the oil in drum x is poured into drum y , then drum y will be filled to what capacity ? \nOptions: a ) 4 / 5 , b ) 8 / 15 , c ) 11 / 15 , d ) 9 / 20 , e ) 13 / 20\nOutput:" }, { "from": "gpt", "value": "e" } ]

[ { "from": "human", "value": "In this task, you need to indicate the presence of temporal reasoning in the provided question. Questions that involve temporal reasoning/understanding contain one of the following five temporal phenomena: First: \"event duration\", is defined as the understanding of how long events last (e.g.,\"brushing teeth\" usually takes a few minutes). Second: \"transient v. stationary\" events, which are based on the understanding of whether an event will change over time or not (e.g., \"being born in the U.S.\" is a stationary event since it will last forever; \"being hungry\" is a transient event since it lasts for a short period of time). Third: \"event ordering\" is the understanding of how events are usually ordered (e.g., \"earning money\" usually comes before \"spending money\"). Fourth: \"absolute timepoint\" of events which is the understanding of when events usually happen (e.g., \"going to school\" usually happens during the day, not at 2 A.M). The last category is \"frequency\" of events, which refers to how often events are repeated (e.g., \"taking showers\" typically occurs ~5 times a week, \"going to Saturday market\" usually happens every few weeks/months, etc.). Indicate with `Yes` if the question involves temporal reasoning. Indicate with `No`, otherwise.\n\nExample Input: Sentence: Thats because the sound couldnt travel without air particles to transfer the sound energy. \nQuestion: Can sound still travel tomorrow?\nExample Output: Yes.\n\nExample Input: Sentence: Some of the people who took advantage of her through a questionable loan program were sent to jail. \nQuestion: Are they still in jail today?\nExample Output: Yes.\n\nExample Input: Sentence: In this way the other major congressional interests can be brought together in the new committee's work. \nQuestion: How often does the committee meet?\nExample Output:" }, { "from": "gpt", "value": "Yes.\n\n" } ]

[ { "from": "human", "value": "Given a sentence, generate what should be the most likely next statement. The next statement should be reasonable and logically correct.\n\nLet me give you an example: We notice a man in a kayak and a yellow helmet coming in from the left. As he approaches, his kayak \nThe answer to this example can be: flips upside - down\nHere is why: Flipping of the kayak is a probable event. It is a logical next statement, given the context.\n\nOK. solve this:\nSomeone beams with newfound optimism. It\nAnswer:" }, { "from": "gpt", "value": ", she sits up again and stretches her hands up." } ]

[ { "from": "human", "value": "You are given a sentence from a conversation between a human and a virtual assistant. Your task is to classify the sentence into one of the following five action categories - INFORM, INFORM_INTENT, OFFER, REQUEST, REQUEST_ALTS. If the sentence is about informing something, generate 'INFORM'. If it is about requesting something, generate 'REQUEST'. If the sentence mentions requesting an alternative option than the one provided, generate 'REQUEST_ALTS'. Similarly, generate 'OFFER' if the sentence is offering some information. If the sentence is about showing intent to do something, generate 'INFORM_INTENT'.\n\nMaybe, I'm interested in finding dates for the event." }, { "from": "gpt", "value": "INFORM_INTENT" } ]

[ { "from": "human", "value": "Teacher:Given a set of four words, generate the category that the words belong to. Words are separated by commas. The possible categories are social gathering, accomodation, physical property, measurement unit, corporate, nutritional value, boats, police punishment, location (proximity), card games, outdoor sport activity, military rank, baby animals, weather, consumer product, animals, boxing terminology, food, chocolate food, bird, type of sandwich, date status, body part, ocean, employment activity, moral characteristic, elements, poker, computers, construction, guitar part, shady activities, physical activity, kitchenware, temperature, type of rigidity, emotional status, season, mode of transportation, window material, activity, emotional display, geographical property, fried food, store status, widespread, aesthetic characteristic, alcoholic drinks, secretary duty, direction, personal characteristic, and animal.\nTeacher: Now, understand the problem? Solve this instance: down, descending, south, up\nStudent:" }, { "from": "gpt", "value": "direction" } ]

[ { "from": "human", "value": "You are given a sentence from a conversation between a human and a virtual assistant. Your task is to classify the sentence into one of the following five action categories - INFORM, INFORM_INTENT, OFFER, REQUEST, REQUEST_ALTS. If the sentence is about informing something, generate 'INFORM'. If it is about requesting something, generate 'REQUEST'. If the sentence mentions requesting an alternative option than the one provided, generate 'REQUEST_ALTS'. Similarly, generate 'OFFER' if the sentence is offering some information. If the sentence is about showing intent to do something, generate 'INFORM_INTENT'.\n\nExample input: Now seems a good moment to watch the movie.\nExample output: INFORM_INTENT\nExample explanation: The user is passively expressing his intent to watch a movie and asking for a suggestion\nQ: Maybe, I'm interested in finding dates for the event.\nA:" }, { "from": "gpt", "value": "INFORM_INTENT" } ]

[ { "from": "human", "value": "The task is to write a full sentence or two using all of the information given. The sentence(s) will be a brief review of a restaurant. Use all of the information provided.\nQ: name[xname], recommend[yes], cuisine[Thai], qual[bad], location[Manhattan], price[cheap]\nA: " }, { "from": "gpt", "value": "I would suggest xname since it provides mediocre food. It is in Manhattan. this place is a Thai restaurant. it's cheap." } ]

[ { "from": "human", "value": "Given a negotiation between two participants, answer 'Yes' if both participants agree to the deal, otherwise answer 'No'.\n\nExample Input: THEM: i take the balls and you can have the rest. YOU: i need 2 balls and a book or a hat THEM: how about 1 ball, a book, and a hat? YOU: ok.\nExample Output: Yes\n\nExample Input: THEM: i want the ball and books. YOU: i want the ball and a book and the hats THEM: give me the ball and one book. you can have the rest. YOU: either the ball and a book, or the ball and both hats. final offer THEM: the hat has no points for me. YOU: i'll take both books and the hats? THEM: yes!\nExample Output: Yes\n\nExample Input: THEM: i need the book and the balls, you can have the hats YOU: negatron megatron i only need those balls THEM: you take the balls and i will take the rest YOU: that works for me.\nExample Output:" }, { "from": "gpt", "value": "Yes\n\n" } ]

[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nGiven a comment text in Tamil, classify the comment into one of these categories (i) Hope speech, if it contains encouraging, positive or supportive contents about equality, diversity or inclusion, (ii) Not Hope Speech or (iii) Not in Expected Language, if the text is not Tamil.\n\nSpr Ithan sariyana valli\nSolution: Hope Speech\nWhy? The given text contains content that is encouraging, positive or supportive contents and talks about equality, diversity or inclusion and is in expected language - tamil\n\nNew input: Madan gowri fans like here\nSolution:" }, { "from": "gpt", "value": "Not in Expected Language" } ]

[ { "from": "human", "value": "In this task, you are given a Reddit post as a text. Your task is to generate a short summary for this text. The summary must include a situation which caused humor. The summary should be one or two sentences long.\nQ: Text: well, it had been a while since i got my bone on. so last night i get to a bar a few hours after most of my friends. my buddy who i showed up with and i decided to play catch-up. so, multiple quick shots of tequila later, i meet this girl and start talking to her. we hit it off and before i know it we are leaving the bar to go to her place. it wasn't until i got there that all the alcohol we'd been drinking hit me... at once... in the face. \n\nso we start getting down to business and she is on top and whispers in my ear, \"i want you to scream my name.\" for the record, i'm into dirty talk. however, at this particular moment, i was very drunk and had forgotten. so i looked at her, terrified. \"uhh... it's.... i know this. give me a second.\" mind is racing like in ted when they're naming white trash names... meghan? rachel? sarah? maggie? kate? sophie? i went blank.\n\nand then... \"i love you.\" why? couldn't tell you. it just felt right. her eyes were like dinner plates. \"you what?\" she asked, in total disbelief. just then, she shifted and went to get off my ween, when i shifted too and... gave her a noodle stab in the butt hole. she rolled off, cursing and grabbing her tush and i moved to the couch, ashamed.\nA: " }, { "from": "gpt", "value": "i am a moron." } ]

[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nYou are given two sentences. You have to find if there is entailment or agreement of the Hypothesis by the Premise. From the given pair of sentences, you should identify if there is enough information in the Premise to support the claim made in the Hypothesis. The Premise may not exactly be the same as Hypothesis. Your task is to return 'entails' if the premise supports hypothesis else return 'neutral'.\n\nPremise: Lyme Disease is caused by a bacterium that's transmitted by tick bite, but many infected people don't remember a bite. \n Hypothesis: Lyme disease is caused by bacteria.\nSolution: entails\nWhy? The premise sentence agrees with the hypothesis that Lyme Disease is a bacterium. The premise also gives additional information about Lyme disease. Therefore Premise entails Hypothesis.\n\nNew input: Premise: A study of the life span of the individual from middle adulthood to later adulthood from a systems perspective with emphasis on interactions with families, groups, organizations, and communities. \n Hypothesis: Menopause occurs in in middle adulthood.\nSolution:" }, { "from": "gpt", "value": "neutral" } ]

[ { "from": "human", "value": "TASK DEFINITION: In this task, you're given a pair of sentences, sentence 1 and sentence 2, that agree with each other. Your job is to alter sentence 2 so that the pair neither agree nor contradict each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence.\nPROBLEM: Sentence 1: A girl wearing a striped shirt, plaid shorts, and a baseball hat is on a bike, pulling a man in a red cart with a black top. Sentence 2: There is a girl on a bike pulling a man.\n\nSOLUTION: The girl is with her father.\n\nPROBLEM: Sentence 1: A man in a black shirt and gloves is welding. Sentence 2: A man working\n\nSOLUTION: A man welding a sword.\n\nPROBLEM: Sentence 1: There is staging and men working on platform 2 at the Burnt Oak underground stop. Sentence 2: There is staging and men working on an underground stop.\n\nSOLUTION:" }, { "from": "gpt", "value": "the man is hungry\n\n" } ]

[ { "from": "human", "value": "In this task, you are given two strings A,B. You must perform the following operations to generate the required output list: (i) Find the longest common substring in the strings A and B, (ii) Convert this substring to all lowercase and sort it alphabetically, (iii) Replace the substring at its respective positions in the two lists with the updated substring.\nOne example: bYubMFxyTqR, AcDbMFxSnI\nSolution is here: bYubfmxyTqR, AcDbfmxSnI\nExplanation: Here, 'bMFx' is the longest common substring in both the input strings 'bYubMFxyTqR' and 'AcDbMFxSnI'. Sorting it and converting to lowercase gives 'bfmx'. Replacing 'bfmx' instead of 'bMFx' in the two strings gives 'bYubfmxyTqR' and 'AcDbfmxSnI'\n\nNow, solve this: zjFJbSXbYRwiMmBdfIcwVynEonwTHRHibpqYjwuG, TyTlWCIoeBBUINZgUdfIcwVynEonwTHRHiWbUootNSsNsF\nSolution:" }, { "from": "gpt", "value": "zjFJbSXbYRwiMmBcdefhhiinnortvwwybpqYjwuG, TyTlWCIoeBBUINZgUcdefhhiinnortvwwyWbUootNSsNsF" } ]

[ { "from": "human", "value": "In this task, you are given a statement spoken by a politician in natural language. Your task is to generate the subject of the discussion for the given statement. The subject generated is not necessarily a part of the given input. Your answer should contain one or more words.\n\nRoy Barnes proclaimed Mexican workers good for Georgia.\neconomy\n\nSays Newt Gingrich said Spanish is the language of the ghetto.\nelections\n\nIn the last six years of Ciancis administration violent crime was down in the United States. It was down in the region. It was down in Rhode Island. But it was up in Providence.\n" }, { "from": "gpt", "value": "crime\n\n" } ]

[ { "from": "human", "value": "In this task, you are given a sentence or phrase in Xhosa. You must translate it to English in a way that is equivalent in terms of meaning and grammatically correct.\nOne example: Ulwakhiwo neempawu zentsinga zemifuno.\nSolution is here: Construction and characteristics of vegetable fibre cordage.\nExplanation: 'Ulwakhiwo neempawu' means construction/make-up and characteristics, 'zentsinga zemifuno' roughly translates to 'of fibre from vegetables'.\n\nNow, solve this: Olu hlobo lumqukumbelo lwaziwa ngokuba ngumqukumbelo okrwada.\nSolution:" }, { "from": "gpt", "value": "Such an edge is known as a raw edge." } ]

[ { "from": "human", "value": "Teacher:You are given a text of the tweet and a corresponding label whether this tweet is 'Offensive', 'Hate Speech' or 'Neither'. Your job is to identify if the label is correct. Generate label 'true' if it's correct, 'false' otherwise.\nTeacher: Now, understand the problem? Solve this instance: Tweet: RT @connorbagen: You know she's a dyke when she asks for men's golf clubs\nLabel: Neither\nStudent:" }, { "from": "gpt", "value": "false" } ]

[ { "from": "human", "value": "Detailed Instructions: In this task, you will be presented with a passage and have to answer a question based on your understanding of the events inferred from the passage. Try to find the best answer that is most likely to fill in \"_\". Note that the URLs in the text have been replaced with [Link].\nQ: (CNN) Recently, Senators John McCain and Lindsey Graham predictably but mistakenly called for greater United States military involvement in the Syrian civil war, proving they have learned nothing from our history in the Middle East. It seems that every dictator and every atrocity in that region is met with a call for action without a thought to consequences. Those who wish to send our soldiers to \"take care\" of every atrocity in the world might want to take a glance at Maplecroft's Human Rights Risk Atlas, which currently lists 35 countries as extreme risks for committing atrocities. Are we prepared to send our military to right the wrongs of all 35 countries?Senators John McCain and Lindsey Graham have advocated for more US military intervention in SyriaSen. Rand Paul: This is a mistake -- we need a new foreign policy doctrine, which states we only intervene if it's in our national security interests \n Question:It is true that the fight against ISIS and the civil war in _ are connected, but not in the way neocons infer.\nA:" }, { "from": "gpt", "value": "Syrian" } ]

[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you are given a sentence which is either in the Gujarati language or English language. You task is to identify the language of input sentence. Input sentence can be in Gujarari or English language only and also it cannot have two languages at a time.\n\nA giant banana is sitting in beach chair which is overlooking turquoise water.\n" }, { "from": "gpt", "value": "English" } ]

[ { "from": "human", "value": "Definition: In this task you will be given a string and you should find the longest substring that is a palindrome. A palindrome is a string that is the same backwards as it is forwards. If the shortest possible palindrome is length 1 you should return the first character.\nInput: yffyfjyffjjyyf\nOutput:" }, { "from": "gpt", "value": "yffy" } ]

[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nYou are given a conversation between two people.'Person1:' and 'Person2:' are used to separate their respective dialogues. You have to classify if there exist more than 2 unique emotions in conversation. If there are more than 2 unique emotions present in the conversation, the output should be classified as '1' else it should be '0'\nExample: Person1: Excuse me , when is the next train to Los Angeles ? \n Person2: 10:15 a . m . \n Person1: Can I get the ticket here ? \n Person2: Sorry . You have to buy your ticket at the next counter . \n Person1: Thank you . \nOutput: 1\nThis conversation has multiple emotions because of unavailability of the ticket at the given counter and the happiness at the end due to gratitude \n\nNew input case for you: Person1: I'm afraid of the darkness . \nPerson2: Don't worry . I'll drive you back . \nPerson1: Thank you . \nOutput:" }, { "from": "gpt", "value": "1" } ]

[ { "from": "human", "value": "In this task, you are given a Reddit post as a text. Your task is to generate a title for this text. The title should start with \"TIFU by\", followed by a situation that caused humor. The title should contain 7-12 words, ideally.\nQ: Text: so i was about to do my grade 6 piano exam soon, but have not signed up for it yet. when i was practicing my piano today (reluctantly), i was thinking about a music lesson i had in school a few days ago. a girl in my class does not take any exams for her piano but has been playing for more than 5 years already. the reason being, she does not enjoy the pressure and stress of an exam. my mother and i have been having quite a few arguments about my piano and i decided i wanted to be like that girl in my class and have piano as a side hobby sort of thing. so i told her i wanted to quit my exam. my mum then went super saiyan mode and went straight for the phone to text my piano teacher about it. she also shouted she is quiting my lessons aswell. i did not want that to happen. i tried to stop her but to no avail. i also tried to tell her about how i was thinking aobut the exam so she could understand. immediately she cut me off and did not want to hear anymore of my \"excuses\". we havent talked to each other since. tension in the house is also high.\n\nany tips for what i can do is also apperciated.\nA: " }, { "from": "gpt", "value": "TIFU by quitting my piano exam." } ]

[ { "from": "human", "value": "TASK DEFINITION: In this task, you are given a review of movie. Your task is to classify given movie review into two categories: 1) positive, and 2) negative based on its content.\nPROBLEM: This is the one movie to see if you are to wed or are a married couple. The movie portrais a couple in Italy and deals with such difficult topics as abortion, infidelity, juggling work and family.The so called \"culture of death\" that we are experiencing nowadays in the world is terrible and this movie will surely make you think.A must see. I hope it gets distributed as it should.Congratulations on the cast and director.Two thumbs up and a 10 star evaluation from me!\n\nSOLUTION: positive\n\nPROBLEM: I read Schneebaum's book (same title as this film) when it was first published and was deeply moved by his ability to see through the many ways of \"otherness\" (his own and the people of the Amazon with whom he lived and loved) to a way of living a decent life. His subsequent books were not as powerful, but showed his continuing quest. His description of his sexual relations with the men of the tribe was way ahead of its time in the early 60's, but his honesty and openness about it were welcome. This movie beautifully conveys both the quirkiness and generosity of the man, but also provides a glimpse into the inevitable destruction of innocence (which is not a morally positive term, in this case) that occurs when \"civilized\" men intrude on traditional societies. Even so, Schneebaum himself has moved into a kind of higher innocence that suggests the possibility of saving humanity from its own destructiveness.\n\nSOLUTION: positive\n\nPROBLEM: A sad, sad sight indeed is The Munster's Revenge. The Munsters are brought back one last time(Fred Gywnne received a huge paycheck to come back to the role of Herman Munster)in this made-for-TV movie about a pair of wax replicas of Grandpa and Herman that are robots \"terrorizing\" the city as preparation for a robbery of a mummy's stash at an exhibit. With the police on their heels, the two elderly television icons try to find out who is actually behind the crimes in order to clear their names. We get to see them dress in drag as waitresses(a minor highpoint in the film), grandpa turns into a bat with attached wire a couple times(one time even flying to Transylvania with Herman somehow invoking his frequent flyer miles I guess), and a most annoying relative \"the Phantom\" constantly sings and breaks glass ad nausium! What is most sad is hard to pinpoint: is it that Gywnne(especially) and Al Lewis look so haggard in every scene and so indifferent to the material. Is it the hokey costumes of the robots that have that school production values look about them. Maybe it is the ridiculous script. Sid Caesar's crazy, mostly unfunny antics. Or perhaps it is seeing something which brought me joy and fond memories as a child being treated to a super K-Mart fashion makeover. At any even, the result is decidedly disappointing and silly even for Munster standards. As for the rest of the cast, Yvonne De Carlo is adequate in a most vacuous role(though showing more cleavage than usual for a woman of her years and experience). K. C. Martell makes an ever-so-not affable Eddie Munster. Jo McDonell is an attractive Marilyn. Bob Hastings as the aforementioned Phantom looks and acts and speaks in the most absurd manner. The film has a real cheap feel about it even for a made-for-TV movie.\n\nSOLUTION:" }, { "from": "gpt", "value": "negative\n\n" } ]

[ { "from": "human", "value": "In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element in the reverse order. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\n\nExample input: 1, 3, ['z', 'h', 'Y', 'U', '2799']\nExample output: Y, h, z\nExample explanation: Here, all the elements between the 1st element and 3rd element in reverse order are 'Y', 'h', and 'z'.\nQ: 6, 7, ['C', 'v', 'f', 'A', 'N', '3085', 'E']\nA:" }, { "from": "gpt", "value": "E, 3085" } ]

[ { "from": "human", "value": "Definition: In this task, you're given the title and three arbitrary sentences out of a five-sentence story. You are also given three additional sentence options, a, b, and c, that may or may not belong to the story. Your job is to pick the two options that seamlessly connect with the rest of the story; note that the selected choices may fit into the story at any point. Indicate your selected choices in order, i.e., as 'ab'/'bc'/'ac' and not as 'ba'/'ca'/'cb'. If options are equally plausible, pick the ones that make more sense.\nInput: Title: I went on a camping trip last Summer. The weather was nice and warm. I am looking forward to my next camping trip. Choices: a. I spent time with friends and family. b. Kate learned to always watch her bird very closely! c. I stayed at the campgrounds for two days.\nOutput:" }, { "from": "gpt", "value": "ac" } ]

[ { "from": "human", "value": "In this task, you will be given a passage, a question and a list of single-word events identified from the passage. The goal is to point out all events from the given event list that can answer the question. If a question is unanswerable or none of the events answer the question, output should be empty.\n\nLet me give you an example: Passage: I submitted the hit. The hit was approved, and then I was paid. Question: What happened after I submitted the hit? Events: ['submitted', 'approved', 'paid'].\nThe answer to this example can be: approved, paid\nHere is why: From the passage, we can infer that events approved and paid happened after the event submitted. Therefore, the answer to this question is \"approved, paid\".\n\nOK. solve this:\nPassage: Moody's assigned a \"Baa 3\" rating to long-term foreign currency debt guaranteed by China International Trust and Investment Corp. Hong Kong (Holdings) Ltd, which owns CITIC Pacific Ltd. It said that the rating reflected \"the critical position\" of CITIC Hong Kong in the group structure of the Beijing-based China International Trust and Investment Corp. Question: What will happen in the future? Events: ['assigned', 'guaranteed', 'owns', 'reflected']\nAnswer:" }, { "from": "gpt", "value": "" } ]