Split (1)

train · 8.3M rows

Search is not available for this dataset

conversations listlengths 2 2
[ { "from": "human", "value": "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\n\nLet me give you an example: Context word: fit.\nThe answer to this example can be: Sentence 1: The trophy doesn't fit into the brown suitcase because _ is too large. \nAnswer1: trophy. \nSentence 2: The trophy doesn't fit into the brown suitcase because _ is too small. \nAnswer2: suitcase.\nHere is why: Here, the two objects are \"trophy\" and \"suitcase\". The trigger words are \"large\" and \"small\". Everything else (apart from the trigger words) are the same in the two sentences. The two sentences have different answers, which are the two objects (\"trophy\" and \"suitcase\").\n\nOK. solve this:\nContext Word: coronary artery disease.\nAnswer:" }, { "from": "gpt", "value": "Sentence 1: Because Steve had coronary artery disease, he chose vegetables over potato chips because eating the _ is worse for his disease. \nAnswer1: potato chips. \nSentence 2: Because Steve had coronary artery disease, he chose vegetables over potato chips because eating the _ is better for his disease. \nAnswer2: vegetables." } ]
[ { "from": "human", "value": "Given a statement about date and time, state whether the statement is true or false. The number of date/time operands in the statement ranges between 2 and 3. Let's say the values are denoted by t1, t2 and t3. The statements follow one of the following ten templates: 't1 occurs before t2, t1 doesn't occur before t2, t1 occurs after t2, t1 doesn't occur after t2, t1 occurs between t2 and t3, t1 doesn't occur between t2 and t3, t1 occured before t2 but after t3, t1 occured after t2 but before t3, t1 didn't occur before t2 but after t3, t1 didn't occur after t2 but before t3'. The output should be either 'True' or 'False'.\n\nExample Input: Apr 20, 2013 occurs between 20 Mar 1988 and May 02, 1993\nExample Output: False\n\nExample Input: 21:08:10 doesn't occur between 7:43:22 and 05:54:07\nExample Output: False\n\nExample Input: 21 Nov 1977 occured before 01 June 1992 but after 15 December 1992\nExample Output:" }, { "from": "gpt", "value": "False\n\n" } ]
[ { "from": "human", "value": "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 - \n '.': Period symbol is used for symbols denoting Punctuations/Separations such as comma, period, backticks etc., \n 'ADJ': Adjectives are words that typically modify nouns and specify their properties or attributes, \n 'ADP': Adposition is a cover term for prepositions and postpositions, \n 'ADV': Adverbs are words that typically modify verbs for such categories as time, place, direction or manner, \n 'CONJ': A word used to connect clauses or sentences or to coordinate words in the same clause, \n 'DET': Determiners are words that modify nouns or noun phrases and express the reference of the noun phrase in context, \n 'NOUN': Nouns are a part of speech typically denoting a person, place, thing, animal or idea, \n '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, \n 'PRT': 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, \n 'PRON': Pronouns are words that substitute for nouns or noun phrases, whose meaning is recoverable from the linguistic or extralinguistic context, \n '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, \n '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, \n 'X': The tag X is used for words that for some reason cannot be assigned a real part-of-speech category.\nExample: Sentence: David A. DiLoreto , president of metal container division , was named -1 to the additional post of group vice president , packaging products , at this packaging {{ , }} industrial and aerospace products concern , -1 succeeding Delmont A. Davis , who T-3 was named -2 president and chief operating officer in August . \nWord: ,\nExample solution: .\nExample explanation: ',' is assigned the period (.) symbol since it denotes a punctuation.\n\nProblem: Sentence: As it stands now , Congress presumes after {{ the }} Reagan administration that the White House will take unconstitutional provisions in appropriations bills -1 lying down . \nWord: the\n" }, { "from": "gpt", "value": "Solution: DET" } ]
[ { "from": "human", "value": "Detailed Instructions: Given a part of privacy policy text, identify the type of personal information which is collected, used, tracked or retained. The type of information should be present inside the given policy text, answer as 'Not Specified' otherwise\nQ: The site collects your cookies or tracking elements for marketing purposes. Collection happens when you implicitly provide information on the website, and your data is identifiable.\nA:" }, { "from": "gpt", "value": "Cookies and tracking elements" } ]
[ { "from": "human", "value": "Definition: Given a sentence, generate what should be the most likely next statement. The next statement should be reasonable and logically correct.\nInput: Someone puts a dagger to someone's throat. Someone\nOutput:" }, { "from": "gpt", "value": "grabs the boy and pushes him out of the way." } ]
[ { "from": "human", "value": "In this task, you're given the title of a five-sentence story and the first four sentences. Your job is to write the last sentence of the story such that it seamlessly connects with the rest of the story.\n\nLet me give you an example: Title: Marcus Buys Khakis. Sentence 1: Marcus needed clothing for a business casual event. Sentence 2: All of his clothes were either too formal or too casual. Sentence 3: He decided to buy a pair of khakis. Sentence 4: The pair he bought fit him perfectly.\nThe answer to this example can be: Marcus was happy to have the right clothes for the event.\nHere is why: Marcus is buying clothes for a business event.\n\nOK. solve this:\nTitle: Pop Cans. Sentence 1: Dave was working in the garage with his Dad. Sentence 2: Half the garage was filled with empty pop cans. Sentence 3: Dave's father told him to recycle the pop cans. Sentence 4: Dave recycled the cans and was given twenty dollars.\nAnswer:" }, { "from": "gpt", "value": "When Dave returned his Father said he can keep the money." } ]
[ { "from": "human", "value": "Definition: In this task, you are given a premise, a hypothesis, and an update. The premise sentence describes a real-world situation and is always assumed to be true. The hypothesis sentence describes an assumption or inference that you might make about that situation having read the premise. The update provides additional information about the situation that might weaken or strengthen the hypothesis. A weakener is a statement that weakens the hypothesis. It makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis. It makes you much more likely to believe the hypothesis is true. Your task is to output 'strengthener' or 'weakener' if the update strengths or weakens the hypothesis, respectively.\nInput: Premise: PersonX hits PersonY hard\nHypothesis: Before, PersonX needed get angry\nUpdate: PersonX wasn't watching as they were skiing down the hill.\nOutput:" }, { "from": "gpt", "value": "weakener" } ]
[ { "from": "human", "value": "Read the given sentence and if it is a general advice then indicate via \"yes\". Otherwise indicate via \"no\". advice is basically offering suggestions about the best course of action to someone. advice can come in a variety of forms, for example Direct advice and Indirect advice. (1) Direct advice: Using words (e.g., suggest, advice, recommend), verbs (e.g., can, could, should, may), or using questions (e.g., why don't you's, how about, have you thought about). (2) Indirect advice: contains hints from personal experiences with the intention for someone to do the same thing or statements that imply an action should (or should not) be taken.\n\nMy mentality is \" with enough money and free time ( since engineers get a lot of PTO and work 5 days a week ) I can follow my dreams then \" Also I 'll tell you now , engineering is almost all programming and physics ." }, { "from": "gpt", "value": "no" } ]
[ { "from": "human", "value": "Instructions: You are given a review about a place. You need to provide a rating from \"1 star\" to \"5 stars\" for this place.\nInput: Went there with a party of 9. I heard they had had some good press and according to the waitress had been overwhelmed with business. The service was SO SLOW that we were there almost 4 hours and not by choice. Not once did a manager or owner show up to offer an apology. The food was better than average, however by the time we got our meals we would have thought a boiled work boot tasty. I won't ever return but hope that they hire enough staff to give better service. There are a ton of quality employees looking for jobs. Hire some if business is so good!!\nOutput:" }, { "from": "gpt", "value": "2 stars" } ]
[ { "from": "human", "value": "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.\nOne example is below.\nQ: Sentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had been shopping in the store.\nA: Tom had been shopping for fruit to give Jon.\nRationale: The given sentence is a good alteration. If the changed sentence was something like: \"Tom had been sleeping in his house in that time\", it'd contradict the first sentence. But this given sentence neither agrees with the first sentence, nor contradicts it.\nQ: Sentence 1: A man smiles while holding a rope on a boat. Sentence 2: a man smiles while holding a rope\nA:" }, { "from": "gpt", "value": "the man was driving his new yacht" } ]
[ { "from": "human", "value": "Detailed Instructions: You are shown a conversation between a user and system. Identify who has spoken the indicated sentence based on the conversation.\nSee one example below:\nProblem: Sentence1:i need a place to dine in the center thats expensive Sentence2: I have several options for you; do you prefer African, Asian, or British food? Sentence3: Any sort of food would be fine, as long as it is a bit expensive. Could I get the phone number for your recommendation?Question: Who has spoken the sentence 2? (A) User (B) System\nSolution: Answer: (A) User\nExplanation: The sentence 1 is said by a user because the intent of it says that the information has to be gathered from the system\n\nProblem: Sentence1: Autumn house. I also need car type and contact number Sentence2: I need to book a taxi to arrive by 18:15 to take me to India House. Sentence3: No problem, but first can you tell me where you need to leave from? Sentence4: Booking completed! Booked car type : red ford Contact number : 07514562305 Question: Who has spoken the sentence 2? (A) User (B) System\nSolution:" }, { "from": "gpt", "value": "Answer: (A) User" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you will be presented with a question, and you have to write the part-of-speech tag for each word in the question. 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\nExample: Who were the builders of the mosque in Herat with fire temples ?\nOutput: WP VBD DT NNS IN DT NN IN NNP IN NN NNS .\nThis is a good example. All of the POS tags are correct.\n\nNew input case for you: What is the national rank in terms of number of flyers of the airport that received 751,791 flyers from the airport in Gimhae in 2018 ?\nOutput:" }, { "from": "gpt", "value": "WP VBZ DT JJ NN IN NNS IN NN IN NNS IN DT NN WDT VBD CD NNS IN DT NN IN NNP IN CD ." } ]
[ { "from": "human", "value": "Definition: In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: toxic and non-toxic. Toxicity is defiend as anything that is rude, disrespectful, or unreasonable that would make someone want to leave a converation.\nInput: Comment: So if the state oil subsidy structure is so flawed why the heck are we electing oil guys to the legislature? Stupid is as stupid does.\nOutput:" }, { "from": "gpt", "value": "Toxic" } ]
[ { "from": "human", "value": "In this task you will be given a string that only contains single digit numbers spelled out. The input string will not contain spaces between the different numbers. Your task is to return the number that the string spells out. The string will spell out each digit of the number for example '1726' will be 'oneseventwosix' instead of 'one thousand seven hundred six'.\nQ: threetwoninesixfivetwo\nA: " }, { "from": "gpt", "value": "329652" } ]
[ { "from": "human", "value": "Instructions: Given a sentence in Dutch, generate a new Dutch 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.\nInput: Een glas water is wat we willen als we dorst hebben.\nOutput:" }, { "from": "gpt", "value": "Een glas water is wat we bieden als we dorst hebben." } ]
[ { "from": "human", "value": "In this task, you have to generate the named entities (NER) given its ingredients of the recipe. Named entities are the names of the items without their quantity.\n--------\nQuestion: 3 eggs, 3/4 cup flour, 3/4 cup sugar, 3/4 cup brown sugar, packed, 1 cup butter, melted, 1 1/2 cups semi-sweet chocolate chips, 1 cup walnuts, coarsley chopped, 9 inches unbaked pie shells, French vanilla ice cream (optional)\n\nAnswer: eggs, flour, sugar, brown sugar, butter, semi-sweet chocolate chips, walnuts, vanilla ice cream\n\n\nQuestion: 2 tablespoons olive oil, 1 medium red onion, 3 garlic cloves, minced, 1/4 teaspoon crushed red pepper flakes (optional), 12 ounces farfalle pasta (bow tie), 1 cup frozen peas, 1 (4 ounce) package smoked salmon, cut into thin strips, 1/4 cup chopped fresh dill, 1 lemon, zest of, salt, pepper\n\nAnswer: olive oil, red onion, garlic, red pepper, pasta, frozen peas, salmon, dill, lemon, salt, pepper\n\n\nQuestion: 12 cup flour, 34 teaspoon baking powder, 14 teaspoon salt, 12 tablespoon maple syrup, 1 egg, 12 cup milk, 1 12 tablespoons shortening\n\nAnswer:" }, { "from": "gpt", "value": "flour, baking powder, salt, maple syrup, egg, milk, shortening\n\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: 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.\nProblem:Category: ACTRESSES \nClue: She was fined 20,000 francs for \"inciting racial hatred\" by denouncing a religious practice of killing sheep\nSolution:" }, { "from": "gpt", "value": "brigitte bardot" } ]
[ { "from": "human", "value": "Definition: In this task you are given a small conversation between two persons and 4 options on how the conversation should continue. Your job is to choose the most reasonable option. The conversation and the options are separated by a newline character. Each dialogue in the conversation are separated by a comma. F and M indicate female and male, respectively.\nInput: M: Oxford Travel Agency, how may I help you? ,F: Hello, I'd like to ask about the package tour from Newcastle to London. ,M: Sure, what's your question? ,F: Your website says that the trip starts off every Thursday. Can I join the trip on July thirtieth? ,M: Sorry, I'm afraid it's full. How many people are going? ,F: My husband and our two children will go with me. ,M: 4 people then. There is still enough places on August sixth. Will that do? ,F: That's fine. Any discount for children under 12? ,M: Sorry, the price for children is the same, 700 pounds each person. It's already cheaper than other agencies.\n(A) F: I'm going alone, so I just need to pay the $700, right? (B) F: 1,400 dollars per person? So it's $2,800 for mom and me. (C) F: I am sorry. You spoke so rapidly that I did not catch the meaning of what you said. Could you repeat that? (D) F: Wow, I will have to pay $3,300 in total for this Oxford trip.\nOutput:" }, { "from": "gpt", "value": "C" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a abstract of article and corresponding title of an article. Your task is to generate label \"yes\" if title is right for article, otherwise generate \"no\".\nSee one example below:\nProblem: Abstract: This study was designed to determine the influence of a long-term, moderate-intensity treadmill training program on the distribution of blood flow within and among muscles of rats during exercise. One group (T) of male Sprague-Dawley rats trained for 1 h/day for 13-17 wk at 30 m/min on a motor-driven treadmill. A second group (UT) of rats was conditioned for 10 min/day for 4 wk at the same speed. Muscle succinate dehydrogenase activities were higher in T than UT rats indicating a significant training effect. Blood flows (BFs) in 32 hindlimb muscles or muscle parts and other selected organs were measured in the two groups with radiolabeled microspheres during preexercise and while the rats ran for 30 s, 5 min, or 15 min at 30 m/min on the treadmill. The data indicate 1) there were no differences in total hindlimb muscle BF between UT and T rats at any time; however, 2) T rats had higher preexercise heart rates and higher muscle BFs in the deep red extensor muscles, suggesting a greater anticipatory response to the impending exercise; 3) T rats demonstrated more rapid elevations in BF in the red extensor muscles at the commencement of exercise; 4) T rats had higher BFs in red extensor muscles during exercise, whereas UT rats had higher BFs in white muscles; and 5) T rats maintained higher BFs in the visceral organs during exercise. These findings demonstrate that exercise training results in changes in the distribution of BF within and among muscles and among organs during exercise. Specifically, data indicate the high-oxidative motor units that are primarily recruited in the muscles during the initial stages of moderate treadmill exercise receive higher blood flows in the trained rats; this presumably contributes to increased resistance to fatigue.. Title: Exercise blood flow patterns within and among rat muscles after training.\nSolution: yes\nExplanation: Title is appropriate for the given abstract because the focus of this abstract is cerebral white matter assesment.\n\nProblem: Abstract: BACKGROUND The increased caloric requirements of HIV-positive individuals, undesirable side effects of treatment that may be worsened by malnutrition (but alleviated by nutritional support), and associated declines in adherence and possible increased drug resistance are all justifications for developing better interventions to strengthen the nutrition security of individuals receiving antiretroviral treatment. \n OBJECTIVE To highlight key benefits and challenges relating to interventions aimed at strengthening the nutrition security of people living with HIV who are receiving antiretroviral treatment. \n METHODS Qualitative research was undertaken on a short-term nutrition intervention linked to the provision of free antiretroviral treatment for people living with HIV in western Kenya in late 2005 and early 2006. \n RESULTS Patients enrolled in the food program while on treatment regimens self-reported greater adherence to their medication, fewer side effects, and a greater ability to satisfy increased appetite. Most clients self-reported weight gain, recovery of physical strength, and the resumption of labor activities while enrolled in dual (food supplementation and treatment) programs. Such improvements were seen to catalyze increased support from family and community. \n CONCLUSIONS These findings provide further empirical support to calls for a more holistic and comprehensive response to the coexistence of AIDS epidemics with chronic nutrition insecurity. Future work is needed to clarify ways of bridging the gap between short-term nutritional support to individuals and longer-term livelihood security programming for communities affected by AIDS. Such interdisciplinary research will need to be matched by intersectoral action on the part of the agriculture and health sectors in such environments.. Title: A genome-wide siRNA screen reveals diverse cellular processes and pathways that mediate genome stability.\nSolution:" }, { "from": "gpt", "value": "no" } ]
[ { "from": "human", "value": "In this task, you're given context and an answer. Your task is to generate the question for this answer based on the given context with commonsense reasoning about social situations..\n\n[Q]: Context: tracy was looking for austin so she went in austin's father's house. \n Answer: he will find tracy\n[A]: What will happen to Austin?\n\n\n[Q]: Context: Addison hadn't been feeling well all day. They decided to leave work early. \n Answer: get home before he felt even worse\n[A]: Why did Addison do this?\n\n\n[Q]: Context: Skylar shot the breeze with some friends she hadn't seen in a while. \n Answer: friendly to almost everyone\n[A]:" }, { "from": "gpt", "value": "How would you describe Skylar?\n\n\n" } ]
[ { "from": "human", "value": "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.\n\n[Q]: Sentence 1: A small tan dog jumps over the barbed wire fence. Sentence 2: A dog is jumping the fence.\n[A]: A little dog is escaping Animal Care and Control.\n\n\n[Q]: Sentence 1: dogs running on a cold but sunny morning Sentence 2: Photo caption dogs running on a cold but sunny morning\n[A]: Black dogs running on a cold but sunny morning\n\n\n[Q]: Sentence 1: A man smiles while holding a rope on a boat. Sentence 2: a man smiles while holding a rope\n[A]:" }, { "from": "gpt", "value": "the man was driving his new yacht\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'. \n\nLet me give you an example: news:According to Gran , the company has no plans to move all production to Russia , although that is where the company is growing .\npolarity:neutral\nThe answer to this example can be: true\nHere is why: Although the author uses negative words like 'no' in the news, there is no evidence of the news begin positive or negative for any stakeholder. Hence, the polarity is neutral and the output is True.\n\nOK. solve this:\nnews:Operating result , excluding one-off items , totaled EUR 9.1 mn compared to EUR 10.6 mn in continuing operations , excluding one-off items in 2004 .\npolarity:negative\nAnswer:" }, { "from": "gpt", "value": "true" } ]
[ { "from": "human", "value": "Q: In this task, you're given a review from Amazon and rating for the product on a scale of 1-5 based on the review. The rating means 1: extremely poor, 2: poor, 3: neutral, 4: good, 5: extremely good. Your task is to generate whether the rating matches the review or not. Answer with \"True\" if the sentence belongs to that section, otherwise answer with \"False\"\nReview: Ok, update to my review... after only 15 months one of the Lasfit bulbs began to flicker on and off. Very disappointing. I was extremely satisfied with the Lasfit headlamps I purchased. A very good value (price was affordable), easy installation (a have a Toyota FJ Cruiser) and great customer support. I recommend Lasfit over the plethora of competitors! The lights produce clean white beams of light, much better than my original factory incandescent bulbs. \n Rating: 2\nA:" }, { "from": "gpt", "value": "True" } ]
[ { "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.\n\nExample input: Passage: Omelettes make a great breakfast , and I enjoy making them because they are very easy to cook . First , I get the eggs out and begin cracking them on the side of the bowl and dumping them into the bowl . I normally use two eggs whites and one whole egg to cut the calories . I add some salt and pepper to the mix for flavor . I pour the mixture into the hot frying pan . I make sure that I add some vegetable oil to the pan before I add the eggs though because I do n't want them to stick . As this occurs , I add some cheese or vegetable to the center of the egg mixture . Really , almost any type of cheese or vegetable makes a good omelette . I then flip one side of the omelette over on to itself to seal in the contents in the middle . It is then ready to serve ! Question: How many times is the omelette flipped? Option1: three times Option2: once\nExample output: once\nExample explanation: As mentioned in the passage that I then flip one side of the omelette; it is clear that omelette is flipped one time only.\nQ: Passage: I look out my window at my front yard and notice that my lawn is growing a little too tall . I think it is time to mow it . I check the sky for rainy clouds to make sure it will not rain soon , and also check the Internet for any rain later today . My lawnmower has a motor and a seat for me to ride in , so it is much easier to use . I go into my garage to make sure my lawnmower has enough gas to work . The lawnmower has plenty of gas and is in good shape , so I turn the key and start its engine . The lawnmower does n't cut the grass unless you pull the lever that controls the blade , so I pull that lever and start to drive the lawnmower over the grass . I make sure the grass is being cut after I drive over it , and carefully steer the lawnmower over all the tall grass in my yard until the grass is cut . Question: Where do they mow the lawn? Option1: back yard Option2: in their front yard\nA:" }, { "from": "gpt", "value": "in their front yard" } ]
[ { "from": "human", "value": "Teacher:In this task, you are given an article. Your task is to summarize the article in a sentence.\nTeacher: Now, understand the problem? Solve this instance: The company says the XMM 6255, with an area of about 300 sq mm, is the world's smallest modem.\nThe standalone chip could be used in wearable tech, as well as security devices such as \"smart\" smoke alarms.\nIt is built to protect against overheating, and withstand tough conditions.\nThe modem also features an embedded power supply.\nSergis Mushell, a research director at analytics company Gartner, said the product signalled Intel's intent to gain a foothold in the mobile connectivity market.\n\"It's not just about the size of it,\" he told the BBC. \"What Intel is really doing is going after a significant stake in the Internet of Things market, where connectivity is most important.\n\"Getting connectivity right is essential for their entire product portfolio,\" he added, referring to Intel's traditional business of making processors.\nHe added that \"anything with a screen will need to have connectivity\" and processors will have to be combined with secure, low-power, connectivity technologies.\nStudent:" }, { "from": "gpt", "value": "Intel has unveiled a 3G modem not much bigger than a UK penny or US one-cent coin, with the aim of embedding it in connected devices around the home." } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given a story (which contains five sentences only). Your task is to find all the characters which are available in the given story.\nProblem:Sentence1: A cat ran around the room. Sentence2: He quickly tired from running. Sentence3: He curled up on the couch. Sentence4: The cat slept all afternoon. Sentence5: When he woke up, he was ready to run around again.\nSolution:" }, { "from": "gpt", "value": "Cat" } ]
[ { "from": "human", "value": "Definition: 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.\nInput: To clean up spilled nail polish.\nOutput:" }, { "from": "gpt", "value": "Pour a large amount of white sauce on top of it. This will make the nail polish clump so you can easily wipe it up." } ]
[ { "from": "human", "value": "Given a story, answer the question about the story. The question is the last sentence in the input. These stories can be difficult due to their length and how each story has at least one of the three following scenarios: the first is when the individual's belief matches reality, the second is when the individual's belief does not match reality, and the third is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios.\nQ: Owen entered the front_yard. Evelyn entered the front_yard. The tangerine is in the green_pantry. Owen moved the tangerine to the blue_container. Ella entered the porch. Mason entered the porch. The celery is in the blue_box. Ella moved the celery to the red_cupboard. Owen is in the front_yard. Mason entered the front_yard. The tangerine is in the blue_container. Owen moved the tangerine to the green_pantry. Evelyn entered the garage. Ella entered the garage. The persimmon is in the red_bottle. Evelyn moved the persimmon to the red_drawer. Where is the persimmon really?\nA: " }, { "from": "gpt", "value": "red_drawer" } ]
[ { "from": "human", "value": "You are given a sentence in Italian. Your job is to translate the Italian sentence into English.\n\nOra un altro problema era che il linguaggio dei libri di testo era davvero incomprensibile." }, { "from": "gpt", "value": "Now another problem was that the language in their textbook was truly incomprehensible." } ]
[ { "from": "human", "value": "Detailed Instructions: 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.\nSee one example below:\nProblem: Passage: Omelettes make a great breakfast , and I enjoy making them because they are very easy to cook . First , I get the eggs out and begin cracking them on the side of the bowl and dumping them into the bowl . I normally use two eggs whites and one whole egg to cut the calories . I add some salt and pepper to the mix for flavor . I pour the mixture into the hot frying pan . I make sure that I add some vegetable oil to the pan before I add the eggs though because I do n't want them to stick . As this occurs , I add some cheese or vegetable to the center of the egg mixture . Really , almost any type of cheese or vegetable makes a good omelette . I then flip one side of the omelette over on to itself to seal in the contents in the middle . It is then ready to serve ! Question: How many times is the omelette flipped? Option1: three times Option2: once\nSolution: once\nExplanation: As mentioned in the passage that I then flip one side of the omelette; it is clear that omelette is flipped one time only.\n\nProblem: Passage: When it was time to clean the floor , the first thing I needed to do was sweep the debris and garbage . I use the broom to sweep the floor from one end to the next , piling all of the dust , dirt and other debris on the floor into a pile in the center of the room . I used a dustpan to collect all the debris , placing it on the floor and using the broom to sweep all of the brie onto the surface of the dustpan . I empty the contents of the dustpan into the garbage then placed the broom and dust pan into the corner . I then made a bucket of water that had floor cleaning solution diluted into it in order to make sites . I took my mop from the corner of the room where the room was , and placed the head of the mob into the water , soaking the head of the mop . Once the head of the mop was completely submerged underwater , and soaking wet , I removed the mop from the bucket and squeeze out the excess water . I ensure that all of the stains and stuck on dirt that was on the floor have been removed with the mop , and that the floor looks spotless including when I finished . I rinsed off the mop with clean water , to remove the left over grime and dirt , and placed the mop in the corner . I also emptied the dirty mop water from the bucket , and placed the empty bucket in the corner as well . Question: What was used to wipe over the entire floor? Option1: A mop Option2: the vacuum\nSolution:" }, { "from": "gpt", "value": "A mop" } ]
[ { "from": "human", "value": "In this task, you are given a sentence and a gender. The sentence mentions two professions: one's gender is unknown and the other's gender can be identified using the gendered pronouns that refer to them in the text. You are expected to return the profession with the given gender.\n\nExample input: Sentence: The carpenter helped the housekeeper to fix the window as she knew nothing about those tools.\n Gender: female\nExample output: Housekeeper\nExample explanation: The housekeeper is a female because of the pronoun \"she\".\nQ: Sentence: The CEO talked to the editor and gave her a raise.\n Gender: female\nA:" }, { "from": "gpt", "value": "Editor" } ]
[ { "from": "human", "value": "We would like you to assess the QUALITY of each of the following argument (discussing Death Penalty) and determine if the argument is Valid or Invalid. A valid argument is clearly interpretable and either expresses an argument, or a premise or a conclusion that can be used in an argument for the topic of death penalty. An invalid argument is a phrase that cannot be interpreted as an argument or not on the topic of death penalty.\n--------\nQuestion: OF THE VICTIM would be able to visit or at least know they're family members are alive if the criminal hadn't KILLED THEM!!\n\nAnswer: Valid\n\n\nQuestion: Many family members who have lost love ones to murder feel that the death penalty will not heal their wounds nor will it end their pain; the extended process prior to executions can prolong the agony experienced by the family.\n\nAnswer: Valid\n\n\nQuestion: Jim, before posting all this garbage on why innocent people are not sentenced to death, maybe you should read this thread first.\n\nAnswer:" }, { "from": "gpt", "value": "Valid\n\n\n" } ]
[ { "from": "human", "value": "Given a sequence of actions to navigate an agent in its environment, provide the correct command in a limited form of natural language that matches the sequence of actions when executed. Commands are lowercase and encapsulate the logic of the sequence of actions. Actions are individual steps that serve as the building blocks for a command. 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'. For commands, 'left' and 'right' are used to denote the direction of an action. 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. Actions and commands do not have quotations in the input and output.\nQ: I_TURN_RIGHT I_RUN I_TURN_RIGHT I_JUMP\nA: " }, { "from": "gpt", "value": "jump right after run right" } ]
[ { "from": "human", "value": "In this task, you will be given a list of numbers. The goal is to divide all the numbers in the list by a constant such that the sum of the resulting list is 1. The output should be rounded to 3 decimals.\n\nEx Input:\n[-6.85, 92.94, 161.85, -63.729, 5.419, -14.353]\n\nEx Output:\n[-0.039 0.53 0.923 -0.364 0.031 -0.082]\n\n\nEx Input:\n[-18.025, 75.885, 143.488, -95.31, 184.245, -12.36, 172.632, 180.918]\n\nEx Output:\n[-0.029 0.12 0.227 -0.151 0.292 -0.02 0.273 0.287]\n\n\nEx Input:\n[-94.101, 84.864, -45.248, 63.031, 145.015, 104.819, -76.134, -64.153]\n\nEx Output:\n" }, { "from": "gpt", "value": "[-0.797 0.719 -0.383 0.534 1.228 0.888 -0.645 -0.543]\n\n\n" } ]
[ { "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.\nExample: Text: 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\nExample solution: TIFU by taking the wrong class for 2 weeks and only realizing it today\nExample explanation: 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\".\n\nProblem: Text: so this happened about 20 minutes ago. as i was driving down my street about to turn right and pull into my driveway, i got distracted by a young girl of about 11 riding her bicycle on the opposite sidewalk right across from my house. what made me catch my eye was her wheel turning left and right as she struggled to keep her balance. her front wheel ended up hitting a telephone pole and she sumersaulted off her bike right onto the sidewalk being the immature young adult that i am, i begin to laugh hysterically; only for a very short period of time... since i got distracted by the little girl falling and i wasn't looking straight, i didn't turn sharp enough and drove right into my neighbours oak tree and fucked up my whole car. her bicycle is in better condition than my car\n" }, { "from": "gpt", "value": "Solution: TIFU by laughing at a little girl and crashing my car" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you're given a statement, the genre to which that statement belongs, and a label indicating if the statement should be agreed with (entailment), disagreed with (contradiction), or neither (neutral). Your job is to write a sentence that describes the genre that follows the tone with respect to the statement, as indicated by the label. If sentence X agrees with sentence Y, the can be concluded from one another. If sentence X disagrees with sentence Y, they can not be correct at the same time. The sentence must also belong to the genre specified.\n\nStatement: I must do this.\nLabel: neutral.\nGenre: fiction.\nOutput:" }, { "from": "gpt", "value": "I must find a way to escape." } ]
[ { "from": "human", "value": "Instructions: You will be given three sentences. Read them, then identify a noun phrase (person, place, or thing) or event that is shared between all three sentences. As the output, write the span of the text corresponding to that phrase in each sentence. Keep the order of the sentences, that is, your answer should look like: 1: a phras from sentence 1e 2: a phras from sentence 2 3: a phrase from sentence 3\nInput: 1: ( CNN ) When ISIS overran their villages near Mosul in August 2014 , a small group of Assyrians , a Middle Eastern minority with a history reaching back more than 4,000 years , picked up weapons and formed their own militia : Dwekh Nawsha -- The Sacrificers . 2: Assyrians belong to the rapidly dwindling Christian population of Iraq -- recent estimates from CAPNI , the largest Christian relief organization in northern Iraq put the number as low as 300,000 compared with 1.5 million 20 years ago -- and many among them see the fight with ISIS as a final battle for survival against the Islamists . 3: After ISIS overran their villages , some Assyrians formed a militia to fight for survival against the terror group .\nOutput:" }, { "from": "gpt", "value": "1: ISIS 2: ISIS 3: ISIS" } ]
[ { "from": "human", "value": "Instructions: 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.\nInput: Category: DURING THE FILLMORE PRESIDENCY \nClue: On August 22, 1851 this U.S. yacht defeated 14 British vessels in a race around the Isle of Wight\nOutput:" }, { "from": "gpt", "value": "the america" } ]
[ { "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.\nCompose a new way to ask the same question. The new question must be asking the exact same thing as the original question does. Without any other information, you should be able to tell that the original question and the new question are the same. Preserve bracketed phrases in your new question. You can change the rest of the question provided the above requirements are satisfied. The new question must have a natural, fluent formulation, as if it were composed by a native English speaker. You will be given three pieces of information to help you create better questions. Those are: \"Answer\": the answer to the question, e.g., \"Honolulu\". \"Answer Type\": the type of the answer, e.g., \"Location\". \"Auxiliary Information\" is a detailed description of some concepts mentioned in the question, if any.\n\noriginal question: Who is the museum director of [Science Museum, London]?\nanswer: Ian Blatchford\nanswer type: Museum director. \nauxiliary information: The Science Museum is a major museum on Exhibition Road in South Kensington, London. It was founded in 1857 and today is one of the city's major tourist attractions, attracting 3.3 million visitors annually. Like other publicly funded national museums in the United Kingdom, the Science Museum does not charge visitors for admission. Temporary exhibitions, however, may incur an admission fee. It is part of the Science Museum Group, having merged with the Museum of Science and Industry in Manchester in 2012.\nSolution: The museum director of the [Science Museum, London] is?\nWhy? The question is correctly paraphrased in this example.\n\nNew input: original question: What type of holiday is [Christmas and holiday season]?\nanswer: us federal holiday, public holiday in nepal, western christian holiday...\nanswer type: Holiday Category.\nauxiliary information: The Christmas season, also called the holiday season, the festive season, or simply the holidays, is an annually recurring period recognized in many Western and Western-influenced countries that is generally considered to run from late November to early January, defined as incorporating at least Christmas and usually New Year, and sometimes various other holidays and festivals. It incorporates a period of shopping which comprises a peak season for the retail sector, and a period of sales at the end of the season. Christmas window displays and Christmas tree lighting ceremonies when trees decorated with ornaments and light bulbs are illuminated, are traditions in many areas. Originally, the term \"Christmas season\" was considered synonymous with Christmastide, a term associated with Yuletide, which runs from December 25 to January 6, popularly known as the 12 Days of Christmas.\nSolution:" }, { "from": "gpt", "value": "What is [Christmas and holiday season] celebrating?" } ]
[ { "from": "human", "value": "Definition: In this task, you are given triplets. Each triplet is in the form of [subject, predicate, object]. Your task is to generate proper sentence that utilizes these triples. The objective is to construct a sentence that (a) captures the facts specified in the triples and (b) is a well-formed sentence easily understandable by a human. All triple values need not be used directly in the sentence as long as the facts are adequately captured.\nInput: [['Jamaal Tinsley', 'NUMBER', '6']]\nOutput:" }, { "from": "gpt", "value": "Jamaal Tinsley wears the number 6." } ]
[ { "from": "human", "value": "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: Question: In a box, there are 8 red, 7 blue and 6 green balls. One ball is picked up randomly. What is the probability that it is neither red nor green?\n\n Option A: 1/3\n\n Option B: 2/5\n\n Option C: 3/7\n\n Option D: 8/27\n\n Option E: 9/29\n\nAnswer: Option A\n\n\nQuestion: Question: The number of diagonals of a polygon of n sides is given by the formula z=n(n-3)/2. If a polygon has twice as many diagonals as sides, how many sides does it have?\n\n Option A: 3\n\n Option B: 5\n\n Option C: 6\n\n Option D: 7\n\n Option E: 8\n\nAnswer: Option B\n\n\nQuestion: Question: What is the greatest prime factor of 4^17 - 2^26?\n\n Option A: 2\n\n Option B: 3\n\n Option C: 5\n\n Option D: 127\n\n Option E: 11\n\nAnswer:" }, { "from": "gpt", "value": "Option D\n\n\n" } ]
[ { "from": "human", "value": "Teacher: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.\nTeacher: Now, understand the problem? Solve this instance: What muscle would you use when playing tennis ?\nStudent:" }, { "from": "gpt", "value": "Good" } ]
[ { "from": "human", "value": "Detailed Instructions: From the given sentence, extract the phrase (often noun or verb) that carries the given relationship. The generated phrase should be present in the sentence.\nProblem:Given Relationship: 'say of', Sentence: 'Jackson had this to say about Odom before the game : \" Lamar is a spontaneous defender .'\nSolution:" }, { "from": "gpt", "value": "say" } ]
[ { "from": "human", "value": "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 and their positions in the sentence order of the story; note that the selected choices may fit into the story at any point. Your answer must be in the form of '2a, 5b', where '2a' means the candidate sentence 'a' will be inserted as the 2nd sentence in the story. The answer must also be in the order of the selected choices, i.e., '2a, 5b' is allowed, and '5b, 2a' is not allowed. If options are equally plausible, pick the ones that make more sense.\n\nEx Input:\nTitle: Terry had terrible anxiety. She was afraid to even order at a restaurant. After being put in a box and cut in half, Terry is now single. Choices: a. Barry was surprised to see that the seeds grew to be sunflowers. b. Terry was so scared to be called on she didn't want to go. c. Her boyfriend took her on a date to a magic show.\n\nEx Output:\n4b, 3c\n\n\nEx Input:\nTitle: Ashley's grandmother had died. Ashley went to the wake to see her grandmother. Ashley began to cry. Choices: a. She was sad to see her grandmother for the last time. b. When I saw the sub, I noticed that the bread was soggy. c. Her mother and relatives hugged and comforted Ashley.\n\nEx Output:\n3a, 5c\n\n\nEx Input:\nTitle: Feeling that he had sufficient knowledge, he decided to go for a ride. Within minutes, he crashed the bike into a mound. Laying in the dirt, he felt foolish for not learning how to ride. Choices: a. He didn't know how to ride it, so he watched videos online. b. Jeff impulsively purchased a new dirt bike. c. The talent scout offered Tim a record deal.\n\nEx Output:\n" }, { "from": "gpt", "value": "2a, 1b\n\n\n" } ]
[ { "from": "human", "value": "You are given a science question (easy-level) and four answer options (associated with \"A\", \"B\", \"C\", \"D\"). Your task is to find the correct answer based on scientific facts, knowledge, and reasoning. 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.\n--------\nQuestion: Which of the following best describes an advantage of using a mass production manufacturing system instead of a custom manufacturing system? \n (A) Customers can provide specific feedback to workers. (B) Workers become skilled in all aspects of assembly. (C) Goods can be easily modified for customers. (D) Products can be made at a lower cost.\n\nAnswer: D\n\n\nQuestion: A geologist finds a layer of shale near the surface from a certain time period. Nearby, the geologist finds the same layer of shale, but it is deeper underground than the first layer. What might have caused the difference in the depth of the shale layer? \n (A) a meteorite (B) a fault (C) ancient fossils (D) animal life\n\nAnswer: B\n\n\nQuestion: Which term identifies a group of cells that work together to perform a similar function? \n (A) molecule (B) organ (C) organism (D) tissue\n\nAnswer:" }, { "from": "gpt", "value": "D\n\n\n" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to collate all the alphabetical elements at the start of the list followed by all the numerical elements of the list. Maintain the order in which the alphabetical elements appear in the given input list, and do the same for the numerical elements.\n\n['4535', '3537', 'r', 'e', 'A']\n" }, { "from": "gpt", "value": "r, e, A, 4535, 3537" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given an article and an answer. Your task is to generate the question for the answer based on the given article.\nProblem:Article: When I first heard about geocaching ,I was skeptical. But the more I thought about it, the more it seemed like an interesting idea.I at least wanted to try it once. Having familiarized myself with how the game works,I set out in search of my first cache. My trip took me through a series of lively hutong ,past a number of small temples, and right into the courtyard of a quiet youth hotel.I spent several minutes looking around, but couldn't find anything. Just before l was about to give up,I spotted a colorful object in the crack of a wall. Could it be the hidden cache? At that moment a group of backpackers amved. According to the game's rules, people who are not in the game must not be allowed to find out about secret caches. So I pretended to make a phone call while waiting for them to leave. When the coast was clear,I grabbed the object. It was the cache! I opened it and pulled out a crumpled sheet of paper with several names and celebratory messages written on it.I added my own and replaced the cache in its hiding place, ready for the next geocacher to find. It may seem like a simple game, but the idea that there are caches hidden all around us is exciting. Once you're hooked, it's easy to set yourself the goal of finding every single cache in a neighborhood or even an entire city. The real treasure, however, is not the cache itself, but the places it takes you to. Hunting for further caches has since introduced me to places which I didn't even know existed. Some are peaceful parks, while others are forgotten historical sites.A few caches have even been in places I passed regularly without giving them any thought. Now,Ifeel a much closer connection. \n Answer: He found it unsuitable for him.\nSolution:" }, { "from": "gpt", "value": "What was the author's initial attitude to geocaching?" } ]
[ { "from": "human", "value": "Detailed Instructions: 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.\nProblem:Category: TOP ATHLETES \nClue: On ESPN's list of the 50 top athletes of the 20th century, this woman is the highest-ranked female\nSolution:" }, { "from": "gpt", "value": "babe didrikson zaharias" } ]
[ { "from": "human", "value": "In this task, you're given a review from Amazon and rating for the product on a scale of 1-5 based on the review. The rating means 1: extremely poor, 2: poor, 3: neutral, 4: good, 5: extremely good. Your task is to generate whether the rating matches the review or not. Answer with \"True\" if the sentence belongs to that section, otherwise answer with \"False\"\nOne example: Review: These are junk! Both bulbs have burned out within a two month period!! I cannot believe that this company can be in business with such poor quality. I have used infrared lights for my ball python for many years now and I get a varied range of months from a bulb, but I have never gone through two bulbs in a matter of two months! I am very disappointed. \n Rating: 1\nSolution is here: True\nExplanation: The user seems very disappointed in the product because the bulb they ordered has been burned out earlier than usual. So, he gave 1 star to the review considering it extremely poor. So, true is the correct answer.\n\nNow, solve this: Review: Purchased this for my son as he is rough on violins. Took it to get it tuned and the bridge put on just to find out the bridge didn't have spaces for the strings to go and that the violin is a toy not a true violin. I was told that by the time I spent the money to make the violin playable I would have spent more than the $250 the store was charging for one of theirs. \n Rating: 2\nSolution:" }, { "from": "gpt", "value": "True" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nThis task is about classifying the similarity of two sentences. The sentences can be classified as (a) SIMILAR - similar to each other, and (b) DISSIMILAR - not similar to each other. Sentences that have the same RDF relationship in terms of [subject, predicate, object] are similar to each other. The input is a list of two sentences and the output is either SIMILAR or DISSIMILAR.\n\n['Antwerp is served by Antwerp International airport.', 'Antwerp International Airport International Airport serves the city of Antwerp.']\nOutput:" }, { "from": "gpt", "value": "DISSIMILAR" } ]
[ { "from": "human", "value": "In this task, you are given an article. Your task is to summarize the article in a sentence.\n\n[EX Q]: However, Better Together leader Alistair Darling said \"there is no way back\" from independence and his campaign would target undecided voters.\nThe latest opinion polls have suggested the vote is too close to call.\nBoth men were speaking to the BBC's Andrew Marr show.\nMr Salmond said: \"We're not aiming to win by one vote. We're aiming to achieve a substantial majority if we can.\"\nHe added: \"We tend to take the attitude that there isn't so much as a 'No' voter in Scotland, there are only deferred 'Yeses', and that's been one of the successes of our campaign.\"\nAsked if he would seek another referendum if there was a \"No\" vote on Thursday, the SNP leader said: \"If you remember that previous constitutional referendum in Scotland - there was one in 1979 and then the next one was 1997.\n\"That's what I mean by a political generation.\n\"In my opinion, and it is just my opinion, this is a once in a generation opportunity for Scotland.\"\nMr Darling commented: \"I said a year ago that this race would narrow as we got towards the wire and that is precisely what has happened.\n\"It's not surprising. It's the biggest single decision we will ever take.\n\"If we vote to leave the UK on Thursday then there's no going back. It's not like an election where you can change your mind if things don't work out.\n\"If things go wrong this time, we've already voted - we're leaving.\n\"There is no way back, which is why in the next five days we will be targeting the 500,000 or so voters who have still got to make their minds up, because the decision is that critical.\"\nHe argued there was uncertainty over whether firms would move their headquarters out of Scotland and over how the NHS and pensions would be funded if the country became independent.\nAnd he argued that \"about a million jobs here in Scotland depend on us being part of the UK\".\nMr Salmond told the Andrew Marr programme that if \"Yes\" won there would \"cease to be a 'Yes' campaign and a 'No' campaign - there will be a Team Scotland\".\nHe said he wanted \"as many voices as possible\" and welcomed an indication from Secretary of State for Scotland Alistair Carmichael last month that he would join such a negotiating team.\nMr Salmond said his negotiating team had \"recruited specialism in a variety of fields\".\nThe first minister renewed his claim that the Bank of England would be \"a shared central bank\" after independence.\n\"There will be a sustainability agreement between the governments in terms of borrowing levels and debt levels,\" he said.\n\"We set that out in our proposals.\"\nThe UK government has said it would not agree to a currency union with an independent Scotland, but Mr Salmond argued American economist Joseph Stiglitz had said \"a shared currency is a very, very viable and common sense thing to do\".\nMeanwhile, Mr Darling again said the pro-Union parties would deliver more powers for the Scottish Parliament if there was a \"No\" vote.\n\"It's quite a clear choice now,\" he said.\n\"We can have faster, safer and better change, reform so that we can strengthen the health service, we can safeguard jobs.\n\"But you don't have the risks that come with independence, to jobs, to the funding of pensions and the health service, the uncertainty about currency.\"\nPressed on whether details of more powers would be available ahead of the vote, the Better Together leader said: \"What has been agreed is the timetable that will bring together the proposals made by the three non-nationalist parties.\n\"Now that's abundantly clear that we will be able to start that process on Friday, if we vote to stay in the United Kingdom.\"\nThe interviews came after Yes Scotland campaigners claimed their private canvassing showed \"the votes are there for a 'Yes' majority\".\nHowever, Better Together said the \"No\" vote was \"holding up\".\nThree polls have put the \"No\" campaign in the lead, while one has put the pro-independence \"Yes\" campaign ahead.\nThe latest poll of polls collating the six most recent surveys - carried out between 9 and 12 September and excluding \"don't knows\" - puts the \"No\" campaign on 51% and the \"Yes\" campaign on 49%.\nThe pro-independence Yes Scotland campaign has not revealed the number of people it has talked to during its private canvassing, but claimed to have achieved a higher return than ever before.\nBetter Together campaign director Blair McDougall said polls showed the referendum vote was \"on a knife-edge\".\nBetter Together published a poll on Saturday suggesting 53.5% opposed independence and 46.5% backed it, when undecided voters were excluded.\nThe telephone poll, commissioned by Better Together from pollsters Survation, reached 1,044 respondents, with an effective sample size of 927.\nConducted between 10 and 12 September, it also pointed to a very high turnout, with 93% of voters surveyed saying they are certain to vote.\nAnother poll for the Observer newspaper, gave the \"No\" campaign a six point lead - 53% to the pro-independence campaign's 47%.\nAnd a new Sunday Times poll - conducted by Panelbase - puts the voters who intended to vote \"No\" on 50.6% while the \"Yes\" campaign was on 49.4%.\nHowever, an ICM poll for the Sunday Telegraph has suggested Scotland could become independent, putting the \"Yes\" camp in the lead. Excluding undecided voters it found \"Yes\" to be on 54% and \"No\" on 46%.\nThe poll was carried out between 10 and 12 September and had a sample size of 705 - smaller than many of the other polls.\nA referendum on whether Scotland should become independent is to take place\nMeanwhile, a leading economist has said there is \"little basis\" for \"fear-mongering\" over the economy of an independent Scotland.\nJoseph Stiglitz countered the view of fellow Nobel prize-winning economist Paul Krugman, who recently warned that Scotland would face \"huge risks\" going it alone and told Scots to \"be very afraid\".\nMr Stiglitz said that while there would be risks in the event of a Yes vote, the risks of Scotland remaining in the union and UK leaving the EU would be \"significantly greater\".\nIn an article published in the Sunday Herald and the Scotsman, he urged Scots to focus on \"vision and values\" in the last few days before the crucial vote.\nHe said: \"Krugman, for instance, suggests that there are significant economies of scale: a small economy is likely, he seems to suggest, not to do well.\n\"But an independent Scotland will still be part of Europe, and the great success of the EU is the creation of a large economic zone.\n\"By an order of magnitude, far more important than size is the pursuit of the right policies.\"\n[EX A]: Scotland's First Minister Alex Salmond said the independence referendum was \"a once in a generation opportunity\" and he was aiming for \"a substantial majority\".\n\n[EX Q]: The fire broke out at Housing Options premises on High Street in the city centre at around 19:20 GMT.\nFire investigators have been at the scene and inquires are continuing.\nAnyone with information about the man or the incident has been asked to call 101.\n[EX A]: Police investigating a suspicious fire at a Swansea council housing office have released images of a man they want to speak to in connection with the blaze.\n\n[EX Q]: Despite 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)\n[EX A]:" }, { "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.\n\n" } ]
[ { "from": "human", "value": "Instructions: Given a negotiation between two participants, answer 'Yes' if both participants agree to the deal, otherwise answer 'No'.\nInput: THEM: hello YOU: hello, you can one ball THEM: i want to keep the hats and the ball? YOU: one book and one vball for you THEM: i want the hats too. a ball and hats. you can have all the books. YOU: no deal THEM: okay. how about i get a hat and a ball? YOU: deal.\nOutput:" }, { "from": "gpt", "value": "Yes" } ]
[ { "from": "human", "value": "TASK DEFINITION: You will be given a sentence containing a pronoun/person name and an emotion. From these implicit parameters, the main goal is to find the gender of the person (male / female).\nPROBLEM: Lakisha found herself in a hilarious situation.\n\nSOLUTION: female\n\nPROBLEM: The conversation with Darnell was shocking.\n\nSOLUTION: male\n\nPROBLEM: The situation makes Darnell feel anxious.\n\nSOLUTION:" }, { "from": "gpt", "value": "male\n\n" } ]
[ { "from": "human", "value": "In this task you will be given a string that only contains single digit numbers spelled out. The input string will not contain spaces between the different numbers. Your task is to return the number that the string spells out. The string will spell out each digit of the number for example '1726' will be 'oneseventwosix' instead of 'one thousand seven hundred six'.\nQ: sevennineeightseveneight\nA: " }, { "from": "gpt", "value": "79878" } ]
[ { "from": "human", "value": "In this task, based on the given context word, you are asked to create a pair of sentences each containing a blank (_). The sentence pair should look similar and should be about two different persons (PersonX and PersonY). Additionally, the two sentences must be different in terms of trigger words (e.g., \"sympathetic\" and \"stern\") which express contrasting attributes about the two persons. The answer to the first and the second sentence must be PersonX and PersonY, respectively. PersonX and PersonY should not be equally likely to fill the blank. 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 the names of real people (e.g., Donald Trump, Putin, etc.) in your sentences. 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 PersonX and PersonY have the same gender. In each sentence, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY.\n\nInput: Consider Input: Context Word: nosebleed.\n\nOutput: Sentence 1: PersonX got a terrible nosebleed while sleeping at PersonY's house, so _ decided to go home. \nSentence 2: PersonX got a terrible nosebleed while sleeping at PersonY's house, but _ didn't want her to go home.\n\n\nInput: Consider Input: Context Word: cashier's check.\n\nOutput: Sentence 1: A cashier's check was received by PersonX by PersonY because _ worked the customer service desk. \nSentence 2: A cashier's check was handed to PersonX by PersonY because _ approached the customer service desk.\n\n\nInput: Consider Input: Context Word: accents.\n\n" }, { "from": "gpt", "value": "Output: Sentence 1: PersonX couldn't understand there accents like PersonY could, because _ was from a different area. \nSentence 2: PersonX couldn't understand there accents like PersonY could, because _ was from the same area.\n\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: You are given a math word problem and you are supposed to apply multiplication or division mathematical operators on the numbers embedded in the text to answer the following question and then only report the final numerical answer.\nSee one example below:\nProblem: Maria has 3 boxes of eggs . Each box holds 7 eggs and there are 8 boxes in a case . How many eggs does Maria have ?\nSolution: 21\nExplanation: Total number of eggs that Maria has is 3*7 = 21\n\nProblem: Patrick jogged to Aaron 's house . It is 14 miles from Patrick 's house to Aaron 's house . It took Patrick 2 hours to get there . How fast did Patrick go ?\nSolution:" }, { "from": "gpt", "value": "7" } ]
[ { "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.\nSee one example below:\nProblem: How do you remove keys from a computer keyboard for cleaning?\nSolution: Place the tip of your finger under the corner of a key and gently twist to pop it off.\nExplanation: The answer is related to the question, but certainly doesn't lead to the asked outcome( A sharp narrow object should be used instead of finger.), so this is a correct answer.\n\nProblem: To clean up spilled nail polish.\nSolution:" }, { "from": "gpt", "value": "Pour a large amount of white sauce on top of it. This will make the nail polish clump so you can easily wipe it up." } ]
[ { "from": "human", "value": "In this task, you're given context and an answer. Your task is to generate the question for this answer based on the given context with commonsense reasoning about social situations..\nExample: Context: Tracy didn't go home that evening and resisted Riley's attacks. \n Answer: Find somewhere to go\nExample solution: What does Tracy need to do before this?\nExample explanation: Tracy has to resist Riley's attack and the answer is she has to find somewhere to go so the question is what does she do before this?\n\nProblem: Context: Natalie was applying to nursing school and asked Lee for a recommendation letter. \n Answer: finish the nursing prerequisites\n" }, { "from": "gpt", "value": "Solution: What did Natalie need to do before this?" } ]
[ { "from": "human", "value": "Detailed Instructions: 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 seamlessly connects with the rest of the story, indicating your choice as 'a' or 'b'. If both sentences are plausible, pick the one that makes more sense.\nProblem:Title: Christmas time. Sentence 1: Last Christmas was amazing. Sentence 2: I visited my family in Philadelphia. Sentence 3: While I was there we sang a lot of carols and ate a lot of chocolate. Sentence 4: On Christmas day we opened all our presents. Choices: a. Now I am a very good dancer. b. I got so many Christmas gifts!\nSolution:" }, { "from": "gpt", "value": "b" } ]
[ { "from": "human", "value": "In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: sexual-explicit and non-sexual-explicit. A comment is considered sexual-explicit if it explicitly portrays sexual matters.\nOne example: Comment: President lied under oath about consensual sex...\nNot the same thing as rape.\nSolution is here: Sexual-explicit\nExplanation: This comment explicitly mentions \"consensual sex\" and \"rape\", and thus is sexual-explicit.\n\nNow, solve this: Comment: The author quotes a professor who states \"police reluctance to work with feminist legal groups mirrors a sentiment common to employees of any company.' Several years ago, I attended a complaint of sexual assault where a woman called to report she had been sexually assaulted at a party. When I got to her home, she was accompanied by a local Rape Relief representative. As I spoke to the woman, I was continually interrupted by the Rape Relief rep, to the extent that I asked her to leave the room. It turned out that the sex was consensual, and that the woman was actually intent on a guilt/revenge thing. What actually happened is that following a fight with her boyfriend, she stormed off, went to the party, got drunk and had sex. Upon returning home, she said \"look what happened to me,\" and then reported it as a rape at the urging of her beau. Unfounded!!!!! \n I also told the Rape Relief worker to go ahead and complain. She never did.\nSolution:" }, { "from": "gpt", "value": "Sexual-explicit" } ]
[ { "from": "human", "value": "Instructions: Given a passage, write a short incorrect summary based on the passage.\nInput: xu kuangdi , vice-chairman of the national committee of the chinese people 's political consultative conference -lrb- cppcc -rrb- , met here wednesday with a delegation of korea junior chamber , inc. , a non-governmental organization of the republic of korea .\nOutput:" }, { "from": "gpt", "value": "interpol asks world govts to make rules for global policing" } ]
[ { "from": "human", "value": "In this task, you are given a short passage that conveys a stereotype or an anti-stereotype. A stereotype is an over-generalized belief about a particular group of people(based on race, ethnicity, gender, age, abilities, etc.). An anti-stereotype is an idea that goes against a common stereotype. You are expected to classify the passage into two classes: stereotype or anti-stereotype.\n\nLet me give you an example: Passage: He couldn't figure out the issue with the rope, but he tried not to get too down on himself, most black kids don't have the best education growing up.\nThe answer to this example can be: Stereotype\nHere is why: This is a stereotype because it is a common mental picture that black kids do not receive proper education growing up.\n\nOK. solve this:\nPassage: I saw the black riders coming, which was odd because I didn't think whites could ride horses.\nAnswer:" }, { "from": "gpt", "value": "Anti-stereotype" } ]
[ { "from": "human", "value": "Given reviews from Amazon, classify those review based on their content into two classes: Negative or Positive.\nQ: Investigators like John Keel don't seem to exist anymore, so get this book while it's still in print for an honest approach toward unexplained phenemenon. It will probably never be able to compete with the books that assure us we are being visited by ET's, angels/demons and/or ancient deities. People want something to believe in. \"Belief is the enemy\",warns Keel. How many paranormal researchers do you know would say that? We are goldfish in a fishbowl being watched over and toyed with, but by What? This is the question Keel will leave you with and that will keep you staring wide eyed up at the ceiling late at night in bed...\nA: " }, { "from": "gpt", "value": "Positive" } ]
[ { "from": "human", "value": "Definition: 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'.\nInput: Query: Tell me about black history. \n Clarification: do you need to know how to trun a grill on\nOutput:" }, { "from": "gpt", "value": "No" } ]
[ { "from": "human", "value": "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. Among the entities, try to find the best entity that is most likely to fill in \"_\" and classify the answers based on options.\nQ: Kiev, Ukraine (CNN) The setting was a Manhattan restaurant, and after 25 minutes what allegedly emerged was a pro-Russian peace plan for Ukraine that its author believes may have ended up in the White House. In a CNN interview, Ukrainian lawmaker Andrii Artemenko said he discussed his left-field proposal for Ukraine in January with US President Donald Trump's personal lawyer, Michael Cohen, who offered to deliver the plan to the Trump administration. The exact details of the plan are unclear, yet reports have suggested it revolves around leasing Crimea -- annexed by Russia from Ukraine in 2014 -- to Moscow for 50 to 100 years. In exchange, Russia would withdraw its troops from the separatist regions in Ukraine's war-torn east.Ukrainian politician says Trump lawyer Michael Cohen offered to deliver peace plan to Michael FlynnCohen says he met with the politician but denies discussing Ukraine peace proposal \n Questions:Cohen told CNN in a text message that although he had dinner with _, they never discussed peace in Ukraine. (A) Kiev (B) Ukraine (C) CNN (D) Manhattan (E) Russian (F) White House (G) Ukrainian (H) Andrii Artemenko (I) US (J) Donald Trump (K) Michael Cohen (L) Trump (M) Crimea (N) Russia (O) Moscow (P) Michael Flynn (Q) Cohen\nA: " }, { "from": "gpt", "value": "(H)" } ]
[ { "from": "human", "value": "Q: Given a scientific question and its correct answer, generate supporting facts for the answer. This supporting fact can be an explanation for the answer to the given question.\nQuestion: Isobaric expansion is a process occurring without a change in what? Answer: pressure\nA:" }, { "from": "gpt", "value": "isobaric expansion is a process occurring without a change in pressure." } ]
[ { "from": "human", "value": "Teacher:In this task, you're given a pair of sentences, sentence 1 and sentence 2. Sentence 2 contradicts sentence 1. 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.\nTeacher: Now, understand the problem? Solve this instance: Sentence 1: Several people are playing baseball on a grassy lawn, with a government building in the background. Sentence 2: Friends playing basketball\nStudent:" }, { "from": "gpt", "value": "Family playing baseball in their backyard" } ]
[ { "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 Twitter posts. Your task is to label the post's emotion (as expressed by the user) as sadness, joy, love, anger, fear, or surprise.\n\ni can almost feel your delicate heart breaking\nOutput:" }, { "from": "gpt", "value": "love" } ]
[ { "from": "human", "value": "In this task, you will be given two sentences sentence1 and sentence2. You should decide whether the second sentence is entailed(agreed) by the first sentence. If it does entail, answer \"yes\", else answer \"no\".\n\nsentence1:employer is crushing employer sentence1:employer is trailing employer " }, { "from": "gpt", "value": "yes" } ]
[ { "from": "human", "value": "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.\n\nExample Input: Title: Joy and Francie made Easter bonnets for the local parade. They took hours to sew individual pieces of candy onto their hats. They displayed them proudly as they walked in the parade. Choices: a. Afterwards they invited all their friends to eat the candy. b. Haley is promoted to a management position at her company. c. Everyone got to enjoy their Easter bonnets!\nExample Output: ac\n\nExample Input: Title: Bob's car broke down in the middle of the road. As soon as it ran, Bob took it into a lot and sold it. He bought a motorcycle and is happier than he ever was with his car. Choices: a. His car had brought him nothing but trouble and pain. b. I took him home and we became best friends. c. As he stood there waiting for help, he had an epiphany.\nExample Output: ac\n\nExample Input: Title: Charlie's class was having a spelling b next month. The winner of the spelling b would win ice cream, Charlies studied hard with the help of his dad. Choices: a. Charlie was shocked and proud when he won. b. Jon was excited when he made an A. c. Charlie wasn't good at spelling but he wanted that ice cream.\nExample Output:" }, { "from": "gpt", "value": "ac\n\n" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task you will be given a list of integers. For every element in the list, if the element is even you should divide by 4, if the element is odd you should multiply by 4 then add 2. The output should be a list of numbers that is the result of applying that logic to the input list. You should not round any decimals in the output. Zero should be counted as an even integer.\n\n[23, -52, 74, 84, 26, -16, 9]\n" }, { "from": "gpt", "value": "[94, -13.0, 18.5, 21.0, 6.5, -4.0, 38]" } ]
[ { "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 seamlessly connects with the rest of the story, indicating your choice as 'a' or 'b'. If both sentences are plausible, pick the one that makes more sense.\nInput: Title: The Confetti. Sentence 1: Calvin was throwing confetti into the air. Sentence 2: It was his birthday and he wanted to celebrate! Sentence 3: He loved throwing big handfuls up over his head. Sentence 4: His friends all joined in. Choices: a. There was a huge mess when they were done. b. The ulcers cleared up.\nOutput:" }, { "from": "gpt", "value": "a" } ]
[ { "from": "human", "value": "In this task you will be given a list of integers. You should find the minimum absolute difference between 2 integers in the list. The absolute difference is the absolute value of one integer subtracted by another. The output should be a single integer which is the smallest possible absolute distance.\n\nInput: Consider Input: [9, -74, -62, -62, 97]\n\nOutput: 0\n\n\nInput: Consider Input: [54, 92, 89, 70, 75, -34, -93, -86, -89]\n\nOutput: 3\n\n\nInput: Consider Input: [-3, -50, -11, 37]\n\n" }, { "from": "gpt", "value": "Output: 8\n\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: sexual-explicit and non-sexual-explicit. A comment is considered sexual-explicit if it explicitly portrays sexual matters.\nSee one example below:\nProblem: Comment: President lied under oath about consensual sex...\nNot the same thing as rape.\nSolution: Sexual-explicit\nExplanation: This comment explicitly mentions \"consensual sex\" and \"rape\", and thus is sexual-explicit.\n\nProblem: Comment: Close your legs if u dont want to get preggo. \n\nGet on birth control even if youre not sexually active and happen to get raped. There are kinds that are good for your skin.\nSolution:" }, { "from": "gpt", "value": "Sexual-explicit" } ]
[ { "from": "human", "value": "Part 1. Definition\nIn this task, you're given the title of a story consisting of five sentences, numbered 1 through 5. Your job is to arrange the sentences in order to make a story that makes complete sense and is apt for the title. Indicate your answer using the number of the sentences in order, such as '34152'.\nPart 2. Example\nTitle: Marcus Buys Khakis. Sentence 1: All of his clothes were either too formal or too casual. Sentence 2: Marcus needed clothing for a business casual event. Sentence 3: The pair he bought fit him perfectly. Sentence 4: Marcus was happy to have the right clothes for the event. Sentence 5: He decided to buy a pair of khakis.\nAnswer: 21534\nExplanation: Marcus's reasons for buying khakis is established, followed by his purchase of them and reaction.\nPart 3. Exercise\nTitle: Depression. Sentence 1: Her psychiatrist diagnosed her with depression after seeing her. Sentence 2: He prescribed an antidepressant for her. Sentence 3: Mary had been feeling depressed lately. Sentence 4: She decided to go to a psychiatrist. Sentence 5: It eventually made her feel better again.\nAnswer:" }, { "from": "gpt", "value": "34125" } ]
[ { "from": "human", "value": "Given a story, answer the question about the story. The question is the last sentence in the input. These stories can be difficult due to their length and how each story has at least one of the three following scenarios: the first is when the individual's belief matches reality, the second is when the individual's belief does not match reality, and the third is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios. Note that there are distractor sentences in each story that are unrelated to the question and are designed to confuse the reader.\n\nOliver entered the porch. Lucas entered the porch. The broccoli is in the green_bucket. Lucas exited the porch. Oliver moved the broccoli to the blue_suitcase. Oliver exited the porch. Lucas entered the porch. Hannah entered the patio. Owen entered the patio. The grapefruit is in the blue_treasure_chest. Owen exited the patio. Hannah moved the grapefruit to the red_treasure_chest. Hannah exited the patio. Owen entered the patio. Lucas is in the porch. Oliver entered the porch. The celery is in the blue_suitcase. Oliver exited the porch. Lucas moved the celery to the green_bucket. Lucas exited the porch. Oliver entered the porch. Hannah entered the lounge. Lucas entered the lounge. The potato is in the green_envelope. Lucas exited the lounge. Hannah moved the potato to the green_pantry. Hannah exited the lounge. Lucas entered the lounge. Where does Hannah think that Lucas searches for the potato?" }, { "from": "gpt", "value": "green_envelope" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task you will be given a list of integers. You should remove all of the integers that are divisible by 3 from the list. If every integer in the input list is divisible by 3 then an empty list should be returned. Zero is divisible by 3.\nExample: [2, 5, 9, 6, 11]\nOutput: [2, 5, 11]\n6 and 9 are removed from the list because they are divisible by 3.\n\nNew input case for you: [-85, 44, 36, 49, 28, 20, 17, -33, 100, -96]\nOutput:" }, { "from": "gpt", "value": "[-85, 44, 49, 28, 20, 17, 100]" } ]
[ { "from": "human", "value": "In this task, answer 'Yes' if the frequency of the given word in the two sentences is equal, else answer 'No'.\nExample: Sentence1: 'a red bus goes down the street beside a yellow building', Sentence2: 'the colorfully decorated living room has a retro style chair in it'. Is the frequency of the word 'beside' in two sentences equal?\nExample solution: No\nExample explanation: Frequency of the word 'beside' in Sentence1 is 1 but 0 in Sentence2. So, the answer is 'No'\n\nProblem: Sentence1: 'a red bench sitting underneath a widow against wall', Sentence2: 'a clock tower stands next to a building above a forest'. Is the frequency of the word 'a' in two sentences equal?\n" }, { "from": "gpt", "value": "Solution: No" } ]
[ { "from": "human", "value": "In this task, you are given commands (in terms of logical operations) and natural interpretation of the given command to select relevant rows from the given table. Your job is to generate a label \"yes\" if the interpretation is appropriate for the command, otherwise generate label \"no\". \n Here are the definitions of logical operators: \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\nCommand: eq { hop { nth_argmin { all_rows ; qual 2 ; 2 } ; name } ; paul tracy }, interpretation: select the row whose qual 2 record of all rows is 2nd minimum . the name record of this row is paul tracy .\nyes\n\nCommand: less { hop { filter_eq { all_rows ; visitor ; cavaliers } ; date } ; hop { filter_eq { all_rows ; visitor ; hornets } ; date } }, interpretation: select the rows whose incumbent record fuzzily matches to chauncey w reed . take the first elected record of this row . select the rows whose incumbent record fuzzily matches to sid simpson . take the first elected record of this row . the first record is less than the second record .\nno\n\nCommand: and { only { filter_eq { all_rows ; party ; independent } } ; eq { hop { filter_eq { all_rows ; party ; independent } ; candidate } ; peter law } }, interpretation: select the rows whose party record fuzzily matches to independent . there is only one such row in the table . the candidate record of this unqiue row is peter law .\n" }, { "from": "gpt", "value": "yes\n\n" } ]
[ { "from": "human", "value": "Q: Categorize the comment on the basis of toxicity. If the comment is toxic (harmful, malicious, derogatory, threat, insult, identity attck, etc.) output Yes, otherwise output No.\nSpot on. The original design was well north of 20 mil, even then they were cheap Charlie plans. And they kept cutting down from there. Kill this dog.\nA:" }, { "from": "gpt", "value": "Yes" } ]
[ { "from": "human", "value": "Teacher:Classify the relation of question with context to one of these categories: 1) award received, 2) based on, collection, 3) conflict, 4) constellation, 5) convicted of, 6) date of death, 7) director, 8) drafted by, 9) educated at, 10) medical condition, 11) military branch, 12) narrative location, 13) occupation, 14) original network, 15) parent company, 16) point in time, 17) production company, 18) residence, 19) series, 20) service entry, 21) sex or gender, 22) spouse, 23) standards body question.\nTeacher: Now, understand the problem? Solve this instance: Context : The Marder I ``Marten'' (SdKfz 135) was a German World War II tank destroyer, armed with the 75 mm anti-tank gun. \nQuestion : What year was the service entry date for Marder I?\nStudent:" }, { "from": "gpt", "value": "service entry" } ]
[ { "from": "human", "value": "In this task, you are given commands (in terms of logical operations) to select relevant rows from the given table. Your job is to classify the command into one of these seven categories: (1) majority, (2) unique, (3) superlative, (4) count, (5) comparative, (6) aggregation, and (7) ordinal. \n Here are the defications of each category: \n 1. majority: Describing the majority values (most or all) over one column, with the scope of all table rows or a subset of rows \n 2. unique: Describing one unique row, regarding one column, with the scope of all table rows or a subset of rows \n 3. Superlative: Describing the maximum or minimum value in a column, with the scope of all table rows or a subset of rows \n 4. Ordinal: Describing the n-th maximum or minimum value in a column, with the scope of all table rows or a subset of rows \n 5. Comparative: Comparing two rows in the table, regarding their values in one column \n 6. Count: counting some rows in the table based on the values in one column, with the scope of all table rows or a subset of rows \n 7. Aggregation: Describing the sum or average value over a column, with the scope of all table rows or a subset of rows. \n Here are the definitions of logical operators for understanding of 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\n[EX Q]: most_eq { all_rows ; type ; end of contract }\n[EX A]: majority\n\n[EX Q]: all_eq { all_rows ; dates ; august }\n[EX A]: majority\n\n[EX Q]: eq { hop { nth_argmax { all_rows ; population ; 3 } ; ethnic group } ; saho }\n[EX A]:" }, { "from": "gpt", "value": "ordinal\n\n" } ]
[ { "from": "human", "value": "In this task, we ask you to write a question that asks about \"event duration\", based on a given sentence. The question will likely start with \"How long\". Your question should be answerable based on the common knowledge of how long certain events usually last. Don't create questions which have explicit mentions of answers in the text. Instead, it has to be implied from what is given. In other words, we want you to use \"instinct\" or \"common sense\". Note that the written questions are not required to have a single correct answer.\nOne example: Sentence: Jack played basketball after school, after which he was very tired.\nSolution is here: How long did Jack play basketball?\nExplanation: the question asks about the duration of an event; therefore it's correct question.\n\nNow, solve this: Sentence: Domestic violence survivors in Jackson, Vicksburg, Hattiesburg, Oxford and Pascagoula can all get help.\nSolution:" }, { "from": "gpt", "value": "How long will the help be offered?" } ]
[ { "from": "human", "value": "instruction:\nThis 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.\nquestion:\nin 2001 , 1,585 persons claimed this nationality , while there were only 1,125 persons declaring solely this nationality in 2011 .\nanswer:\nin 2001 , 1,585 people signed up to it , while in 2011 only 1,125 people exclusively signed up to this nationality .\n\n\nquestion:\nit 's only sold in surgical supply stores .\nanswer:\nhe 's only sold in a surgical dressing shop .\n\n\nquestion:\nwell , you 're supposed to check in every two hours .\nanswer:\n" }, { "from": "gpt", "value": "you should have logged in every two hours .\n\n\n" } ]
[ { "from": "human", "value": "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 fine 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 : '$': Dollar Sign, \"''\": Single Quotes, ',': Comma Symbol, '-LRB-': Left Parantheses, '-RRB-': Right Parantheses, '.': Period, ':': Colon, 'ADD': Email Address, 'AFX': Affix, 'CC': Coordinating conjunction, 'CD': Cardinal Number, 'DT': Determiner, 'EX': Existential there, 'FW': Foreign Word, 'GW': Go with, 'HYPH': Hyphen symbol, 'IN': Preposition or a subordinating conjunction, 'JJ': Adjective, 'JJR': A comparative Adjective, 'JJS': A Superlative Adjective, 'LS': List item Marker, 'MD': Modal, 'NFP': Superfluous punctuation, 'NN': Singular Noun, 'NNP': Singular Proper Noun, 'NNPS': Prural Proper Noun, 'NNS': Prural Noun, 'PDT': Pre-determiner, 'POS': Possessive Ending, 'PRP': Personal pronoun, 'PRP$': Possessive Pronoun, 'RB': Adverb, 'RBR': Comparative Adverb, 'RBS': Superlative Adverb, 'RP': Particle, 'SYM': Symbol, 'TO': To , 'UH': Interjection, 'VB': Base form Verb, 'VBD': Verb in Past tense, 'VBG': Verb in present participle, 'VBN': Verb in past participle, 'VBP': Verb in non-3rd person singular present, 'VBZ': Verb in 3rd person singular present, 'WDT': Wh-determiner, 'WP': Wh-pronoun, 'WP$' Possessive Wh-pronoun, 'WRB': Wh-adverb, 'XX': Unknown, '``': Double backticks.\n--------\nQuestion: Sentence: Once you 've buttered them up a bit try to get them to the pet store and ask one of the employees {{ to }} handle the snake showing your mom how gentle and harmless they can be . \nWord: to\n\nAnswer: TO\n\n\nQuestion: Sentence: When Iraq invaded Kuwait , many of these girls were transported to Jordan and then {{ smuggled }} to various countries -- Germany , France , Canada , Denmark , England , the United States -- where they were raised by guardians who were usually Mujahedeen supporters . \nWord: smuggled\n\nAnswer: VBN\n\n\nQuestion: Sentence: Even for {{ those }} who later abstain , \" visual - spatial abilities , abstraction , problem solving , and short - term memory , are the slowest to recover . \" \nWord: those\n\nAnswer:" }, { "from": "gpt", "value": "DT\n\n\n" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. 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 return the sum of all the numerical elements in the list A between the positions i and j (including positions i and j). Return 0 if no numerical element is present in the list between the given ranges. 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\n1, 11, ['G', 'o', 'U', 'Q', 'J', '6495', 'z', '2903', '3557', 'p', '7351', 'v', 'q', '1591', '245', 'f']\n" }, { "from": "gpt", "value": "20306" } ]
[ { "from": "human", "value": "In this task, you are given a list of unique integers you need to swap the positions of maximum and minimum element in the list and return the updated list.\nQ: [53, 400, 447, 274, 435, 432, 46, 51, 317, 404, 442, 16, 70, 190, 449, 43, 356, 156, 175, 294]\nA: " }, { "from": "gpt", "value": "[53, 400, 447, 274, 435, 432, 46, 51, 317, 404, 442, 449, 70, 190, 16, 43, 356, 156, 175, 294]" } ]
[ { "from": "human", "value": "Detailed Instructions: Given a question and its paraphrases, answer the question. The answer should exactly answer all the questions given without any ambiguity. Don't give partial answers.\nSee one example below:\nProblem: Questions: ['what is the amount of us representatives of nevada?', 'what are the us representative number for nevada?','what is the number of us representatives in nevada?']\nSolution: 4\nExplanation: The output answer is the exact answer for the given questions\n\nProblem: Questions: ['when did the english civil war start?']\nSolution:" }, { "from": "gpt", "value": "1642-08-22" } ]
[ { "from": "human", "value": "Instructions: In this task, you're given a dialogue between a customer and a flight booking agent with a gap in the conversation. Your job is to find the answer of the previous dialogue. Avoid using irrelevant extra information while creating the answer. The answer should be relevant to the question before the blank. If you fill the blank with a question, it should have an answer from the agent in the given dialogue. Fill the gap marked with underline.\nInput: customer: Hi. \n agent: Hello. How can I help you? \n __ \n agent: Please wait a moment to check the reservation status. \n customer: Sure. \n agent: Sorry, no reservation found by your name. \n customer: Not an issue. Anyway, thank you for checking. \n agent: Thanks.\nOutput:" }, { "from": "gpt", "value": "customer: I am Patricia Baker. I want to stay for some more days at Minneapolis, can you please help me to change my flight reservation?" } ]
[ { "from": "human", "value": "TASK DEFINITION: Given a disfluent sentence, modify the sentence to it to its equivalent fluent form, preserving the meaning of the sentence.\nPROBLEM: Who didn't George er uh Dinwiddie order to address French in Virginia territory?\n\nSOLUTION: Who didn't Dinwiddie order to address French in Virginia territory?\n\nPROBLEM: Which or no make that what division offers more than one branch of studies that don't fit in with the other four?\n\nSOLUTION: What division offers more then one branch of studies that don't fit in with the other four?\n\nPROBLEM: What does instead why does unemployment harm growth?\n\nSOLUTION:" }, { "from": "gpt", "value": "Why does unemployment harm growth?\n\n" } ]
[ { "from": "human", "value": "Read the passage and find the corresponding person for the given pronoun. The word between is the target pronoun.\n\nLet me give you an example: The current members of Crime have also performed in San Francisco under the band name ''Remote Viewers``. Strike has published two works of fiction in recent years: Ports of Hell, which is listed in the Rock and Roll Hall of Fame Library, and A Loud Humming Sound Came from Above. Rank has produced numerous films (under his real name, Henry Rosenthal) including the hit The Devil and Daniel Johnston.\nThe answer to this example can be: Henry Rosenthal\nHere is why: The person's name is referenced next to the pronoun itself. Therefore it is clear 'Henry Rosenthal' is the correct answer.\n\nOK. solve this:\nAyaan Hirsi Ali is not one of them,'' she added. Ibrahim Hooper, a spokesman for the Council on American-Islamic Relations, condemned her ``one of the worst of the worst of the Islam haters in America, not only in America but worldwide.'' In his 2006 review of this collection of seventeen essays and articles on Islam by Hirsi Ali, journalist Christopher Hitchens noted her three themes: ``first, her own gradual emancipation from tribalism and superstition; second, her work as a parliamentarian to call attention to the crimes being committed every day by Islamist thugs in mainland Europe; and third, the dismal silence, or worse, from many feminists and multiculturalists about this state of affairs.''\nAnswer:" }, { "from": "gpt", "value": "Christopher Hitchens" } ]
[ { "from": "human", "value": "Part 1. Definition\nIn this task, you are given inputs 'i', 'j', and A, where 'i' and 'j' are integers and A is a list. A list is shown by two brackets and comma-separated numbers and characters inside, like ['1', '12', 'l']. You need to concatenate all elements of A from the ith element to the jth element, and then reverse the resulting string. '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'. Perform the operations in order, i.e., do not reverse first and then concatenate.\nPart 2. Example\n1, 3, ['238', 'h', '92', 'U', '2799']\nAnswer: 29h832\nExplanation: Here, concatenating all the elements between the 1st element and 3rd element and then reversing the string gives '29h832'.\nPart 3. Exercise\n10, 27, ['407', 'b', 's', '3171', '8461', '4681', '5237', 't', '5871', '447', 'S', 'c', 'd', '1421', '3011', '821', '8683', '3203', '2079', 'N', 'F', 'E', 'H', '8773', '2259', 'K', 'f']\nAnswer:" }, { "from": "gpt", "value": "fK95223778HEFN97023023386812811031241dcS744" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a abstract of article and corresponding title of an article. Your task is to generate label \"yes\" if title is right for article, otherwise generate \"no\".\nProblem:Abstract: Recently many exciting advances have been achieved in our understanding of Drosophila meiosis due to combined cytological and genetic approaches. New techniques have permitted the characterization of chromosome position and spindle formation in female meiosis I. The proteins encoded by the nod and ncd genes, two genes known to be needed for the proper partitioning of chromosomes lacking exchange events, have been identified and found to be kinesin-like motors. The effects of mutations in these genes on the spindle and chromosomes, together with the localization of the proteins, have yielded a model for the mechanism of female meiosis I. In male meiosis I, the chromosomal regions responsible for homolog pairing have been resolved to the level of specific DNA sequences. This provides a foundation for elucidating the molecular basis of meiotic pairing. The cytological techniques available in Drosophila also have permitted inroads into the regulation of sister-chromatid segregation. The products of two genes (mei-S332 and ord) essential for sister-chromatid cohesion have been identified recently. Additional advances in understanding Drosophila meiosis are the delineation of a functional centromere by using minichromosome derivatives and the identification of several regulatory genes for the meiotic cell cycle.. Title: Tumor engraftment in nude mice and enrichment in stroma- related gene pathways predict poor survival and resistance to gemcitabine in patients with pancreatic cancer.\nSolution:" }, { "from": "gpt", "value": "no" } ]
[ { "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.\nIn this task, a passage will be given and the goal is to generate a question about temporal relations based on that passage. A temporal relation describes the relation between two things with respect to time e.g., something happens/starts/terminates/... immediately/shortly/usually/... before/after/during/... something else.\n Your question should include an event, or ask about an event, and should not be a yes/no question.\n\nPassage: I submitted the hit. The hit was approved, and then I was paid.\nSolution: What happened after I submitted the hit?\nWhy? This is a valid temporal question based on the given paragraph. Events approved and paid have a temporal relation \"after\" with the event submitted.\n\nNew input: Passage: He also said the bilateral economic and trade cooperation had seen rapid development and that his government is implementing big projects funded by Chinese loans. Enkhbayar said that during his visit, the two sides would discuss how to expand cooperation in economy, trade and other fields.\nSolution:" }, { "from": "gpt", "value": "What event has already finished?" } ]
[ { "from": "human", "value": "In this task, you are given a post in English from online platforms. You are expected to identify whether the post is hateful against immigrants and women. A hateful post expresses hate or encourages violence towards a person or a group. If a post is hateful but not towards immigrants and women, it should be labeled as non-hateful. Answer \"hateful\" or \"Non-hateful\". Note that the URLs in the text have been replaced with [Link].\n\nPost: If your in a good relationship, it's probably cause you're both ugly" }, { "from": "gpt", "value": "Non-hateful" } ]
[ { "from": "human", "value": "Instructions: You're given a fill-in-the-blank question where the answer is PersonX. You need to minimally change the given question so that the answer flips to PersonY. This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"sympathetic\" to \"stern\"). You should not change any content in the given question beyond a word or two i.e. the trigger word/phrase. PersonX and PersonY should not be equally likely to fill the blank. For your question, PersonY should be a well-agreed answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people or generic names (e.g., Donald Trump, John Doe, etc.) in your question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that PersonX and PersonY have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY. Although there are many correct answers, you only need to write one of them.\nInput: Context Word: mold. \nQuestion: PersonX had to remove a lot of mold from his house compared to PersonY, because _ lives in a humid area. \nAnswer: PersonX\nOutput:" }, { "from": "gpt", "value": "PersonX had to remove less mold from his house compared to PersonY, because _ lives in a humid area." } ]
[ { "from": "human", "value": "Teacher:In this task you will be given a list of integers. You should find the maximum absolute difference between 2 integers in the list. The absolute difference is the absolute value of one integer subtracted by another. The output should be a single integer which is the largest possible absolute distance.\nTeacher: Now, understand the problem? Solve this instance: [44, -37, -74, 13, -43, -60, -85, 48, -8]\nStudent:" }, { "from": "gpt", "value": "133" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nGiven an entity as input, output another entity which is part of the input entity. These are entities of meronym. In linguistics, meronymy is a semantic relation between a meronym denoting a part and a holonym denoting a whole. In simpler terms, a meronym (i.e., output entity) is in a part-of relationship with its holonym (i.e., input entity).\n\nprotosteles\nOutput:" }, { "from": "gpt", "value": "xylem element" } ]
[ { "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 find all elements of A from the ith element to the jth element, reverse the order in which they occur, and then concatenate them to output the resultant string. 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. Perform the operations in order, i.e., do not concatenate the elements and then reverse the string.\n20, 21, ['D', 'B', 'j', '5971', '8339', '3269', '653', 'y', '8069', '6197', 'j', 's', '6143', 'G', 'i', '4857', 'O', '7781', 'Q', '3445', '5543', '1693', 'l', 'v', 'd', 'k']\nA:" }, { "from": "gpt", "value": "55433445" } ]
[ { "from": "human", "value": "In this task, you need to reverse all words of a given length in the sentence. The number of letters in a word determine its length. For example, the length of the word \"apple\" is 5.\nQ: Sentence: 'some people on a beach with many kites in the sky'. Reverse all words of length '2' in the given sentence.\nA: " }, { "from": "gpt", "value": "some people no a beach with many kites ni the sky" } ]

Subsets and Splits

No community queries yet

The top public SQL queries from the community will appear here once available.