Split (1)

train · 8.3M rows

Search is not available for this dataset

conversations listlengths 2 2
[ { "from": "human", "value": "In this task you are given a medical question pair hand-generated. Your task is to classify a given post into two categories 1) 'Similar' if the given two questions have a same connotation 2) 'Dissimilar' if the given two questions have a different connotation or meaning.\nQ: Sentence1: Rcently prescribed Lumigan 0.1% IOP concern about burning in eyes called the Doc and Doc does not take calls. What to do? Next appt in a week? \n Sentence2: What is Lumigan 0.1% used for? Can it cause redness or burning in the eyes?\nA: " }, { "from": "gpt", "value": "Dissimilar" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. Given 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\nlarge , rounded head\n" }, { "from": "gpt", "value": "eye" } ]
[ { "from": "human", "value": "Teacher:You are given a paragraph, with numbered sentences, and a question. Write the numbers of the sentences needed to answer the given question. Separate multiple sentence numbers with a comma (\", \"). E.g. \"1, 2\" would be the correct response if Sent 1 and Sent 2 are needed to answer the given question (do not include sentences that contain no information that is necessary to answer the question). Sort the sentence numbers in an increasing order (i.e., '1, 2', instead of '2, 1'). Your answer should not contain anything than the sentence numbers separated by a comma (e.g. '1, 2, 3, 4'). The given question requires more than one sentence to answer. So, your answer must contain at least one comma (\", \").\nTeacher: Now, understand the problem? Solve this instance: Paragraph- Sent 1: The year is 1980 , and the film opens with the launch of the JX-1 Hayabusa spaceship into outer space .\nSent 2: The ship , originally sent to collect data on Saturn , has its course diverted to investigate the mysterious star Gorath , reported as being 6000 times the size of the Earth .\nSent 3: It is feared that the star 's path could come dangerously close to Earth .\nSent 4: The JX-1 reaches locates Gorath and it 's much smaller than earth but with 6000 times the gravity .\nSent 5: The JX-1 radio 's back any data about the star but gets sucked into the star 's gravitational field which drags the ship into Gorath , incinerating it .\nSent 6: Japan and the rest of the world are stunned by the discovery and , after some reluctance , send up the JX-2 Ootori spaceship for a voyage to investigate Gorath .\nSent 7: The United Nations band together to discover a solution to the problem , and decide that their only solutions are to either destroy Gorath or move the planet out of the way .\nSent 8: Back on Earth , the UN decides on the plan to move the Earth out of the way of Gorath , the South Pole Operation .\nSent 9: The plan is to have atomic energy channeled through huge atomic furnaces 500 meters below the surface , then fed though enormous pipes called thrusters which will all fire in unison .\nSent 10: But for this to work they will need an area 600 kilometers producing an atomic force equal to that of 6,600,000,000 megatons to move the Earth 400,000 kilometers way from Gorath .\nSent 11: This massive project meets some setbacks such as cave-ins , but presses on . \nQuestion: How does the JX-1 Hayabusa spaceship mission change after it's launch into outer space?.\nStudent:" }, { "from": "gpt", "value": "1, 2, 3." } ]
[ { "from": "human", "value": "In this task, you are given a dialogue from a conversation between an agent and a customer. Your task is to determine the speaker of the dialogue. Answer with \"agent\" or \"customer\".\n\n[Q]: I found a flight with your requirements in Hawaiian airlines.\n[A]: agent\n\n\n[Q]: Hello, how may I be there for you?\n[A]: agent\n\n\n[Q]: Sure, you can.\n[A]:" }, { "from": "gpt", "value": "customer\n\n\n" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you're given the title of a story consisting of five sentences, numbered 1 through 5. Your job is to determine which two sentences need to be swapped sentences in order to make a story that makes complete sense and is befittingly titled. Indicate your answer using the numbers of the two sentences in order, such as '34' or '25'. The first digit refers to the sentence which should come first in the story.\n\nTitle: Melted. Sentence 1: She resolved to ask for napkins next time! Sentence 2: When Kia saw the ice cream truck, she ran to get ice cream! Sentence 3: But as she ate it, it dripped everywhere. Sentence 4: More of it melted than Kia could eat! Sentence 5: It was a very hot summer day.\n" }, { "from": "gpt", "value": "51" } ]
[ { "from": "human", "value": "TASK DEFINITION: In this task, you are given a dialogue between a user and an assistant, where users and assistants converse about geographic topics like geopolitical entities and locations. The task here is to find if the dialogue is by the user or assistant. Classify your answers into user and assistant.\nPROBLEM: Palestine was shortly admitted into the Arab League.\n\nSOLUTION: assistant\n\nPROBLEM: A lot of their laws were compiled in English but since 1987 government directive laws are now mainly written in Bengali.\n\nSOLUTION: assistant\n\nPROBLEM: I'd like to see that. What sort of transport is commonly used?\n\nSOLUTION:" }, { "from": "gpt", "value": "user\n\n" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nGiven reviews from Amazon, classify those review based on their content into two classes: Negative or Positive.\nExample: I've read this book with much expectation, it was very boring all through out the book\nOutput: Negative\nReview writer does not like the book because it was boring, therefore it is a negative review.\n\nNew input case for you: This movie was HORRIBLE! I don't know how anyone could give it 5 stars. This movie was the worst 2 hours of my life. I expected more out of an Adam Sandler movie. I felt like I was watching 2 movies at once. Any time someone asks me about this movie I tell them it's a waste and to rent something else.\nOutput:" }, { "from": "gpt", "value": "Negative" } ]
[ { "from": "human", "value": "In this task, you need to count the number of words in a sentence that start with the given letter. Answer with numbers and not words.\nOne example is below.\nQ: Sentence: 'a hot dog in a bun with ketchup on a plate with french fries'. How many words start with the letter 'a' in the sentence.\nA: 3\nRationale: The word 'a' is the only word that starts with 'a'. This sentence has 3 occurrences of the word 'a'. So, the answer is 3.\nQ: Sentence: 'a dog waiting patiently in the bed of a truck'. How many words start with the letter 'o' in the sentence.\nA:" }, { "from": "gpt", "value": "1" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given the beginning and the ending of a three-part story. Your job is to complete the short story by writing a middle sentence that seamlessly connects the first and last sentence. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra information when creating the middle sentence, and use names (e.g. Jack, Barbara,...) instead of pronouns (e.g. he / she) wherever possible.\nProblem:Beginning: Thomas is starting his first job at McDonald's Ending: He decided that he's going to start a lawn-mowing business instead.\nSolution:" }, { "from": "gpt", "value": "Things didn't go well at McDonalds." } ]
[ { "from": "human", "value": "Teacher: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'.\nTeacher: Now, understand the problem? Solve this instance: Query: Where can I find cheap internet \n Clarification: are you wondering how to reduce your internet bill\nStudent:" }, { "from": "gpt", "value": "Yes" } ]
[ { "from": "human", "value": "Detailed Instructions: You will be given a piece of text either about an everyday event, or a general statement. If the event seems a plausible event to you, or the general statement makes sense matches your commonsense, output 'True', otherwise output 'False'.\nProblem:It is easier to run 100 feet than 500 feet.\nSolution:" }, { "from": "gpt", "value": "True" } ]
[ { "from": "human", "value": "Read the given query and classify it as a 'Good' or 'Bad' query depending on how well the query is formed, 'Bad' being the expected output for a not so well formed query and 'Good' being the expected output for a well formed query. A query may be wrong based on common sense or general facts, but if it is well formed, you should answer with Good.\nQ: What is the remedy to superstition ?\nA: " }, { "from": "gpt", "value": "Good" } ]
[ { "from": "human", "value": "In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element in the reverse order. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\n\nLet me give you an example: 1, 3, ['z', 'h', 'Y', 'U', '2799']\nThe answer to this example can be: Y, h, z\nHere is why: Here, all the elements between the 1st element and 3rd element in reverse order are 'Y', 'h', and 'z'.\n\nOK. solve this:\n5, 5, ['2927', 'M', '5407', '3991', '387', 'b']\nAnswer:" }, { "from": "gpt", "value": "387" } ]
[ { "from": "human", "value": "Q: In this task, you're given a context passage, a question, and three answer options. Your task is to return an incorrect answer option to the question from the choices given. For all questions, only one of the three answer options is correct. Pick one of the two incorrect answer options as the output.\nContext: i got into a fight with cameron and he decided he would break my leg. \n Question: What does Cameron need to do before this? \n Options: (A) berate cameron (B) break up the fight (C) think about how he can break a leg\nA:" }, { "from": "gpt", "value": "A" } ]
[ { "from": "human", "value": "Detailed Instructions: This task is about translating a given Spanish language sentence to English.\nProblem:Ya le dije al siguiente que se encargue de el.\nSolution:" }, { "from": "gpt", "value": "Our people will deal with him." } ]
[ { "from": "human", "value": "In this task you will be given a process, and a question. The process contains a sequence of steps that happen in order. The question asks about the effect of a certain event on another event. If the first event has a positive effect on the second event, answer with \"for\", if it has a negative effect, answer with \"against\". If there's no causal relationship between the two, answer with \"none\".\nQ: Process: -The kidneys receive blood from the renal artery -They process it with millions of tiny nephrons -Remove all the waste -The kidneys return the blood back to the body through the renal artery -Send the urine with the waste to the bladder through the ureters.\n Question: What is the effect of the person is on dialysis on kidneys produce urine after filtering the blood.?\nA: " }, { "from": "gpt", "value": "against" } ]
[ { "from": "human", "value": "Teacher:The task is to generate text based of an event. For the given event, there will be a person who does the action in the event (usually PersonX). Your task is to write that persons emotional reaction to the event, i.e. how that person feels after doing the action.\nTeacher: Now, understand the problem? Solve this instance: PersonX invites all of PersonX's friends over\nStudent:" }, { "from": "gpt", "value": "happy" } ]
[ { "from": "human", "value": "You are asked to create a question containing a blank (_), based on the given context word. Your question must contain two related but different objects; for example \"trophy\" and \"suitcase\". The expected answer to your question must be one of the objects present in the sentence. The expected answer must not be associated with any specific word in the question; instead it should depend on the context present in the question. The expected answer should not be equally likely to fill the blank. For your question, there should be a agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use animals or proper nouns (e.g., New York, Macbook, Jeff Bezos, McDonald's, ...) as your objects. Avoid repeating the same style, pattern or phrases in each question, try to increase diversity by varying sentence structure, blank placement etc. Your question must contain at least 15 and at most 30 words. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that Object X and Y have the same number e.g. when ObjectX is singular, Object Y must be singular, too. The two objects (Object X & Object Y) should be used ONCE in your question. Here is a list of attributes and associated pair of contrastive words which may be used to create a valid question using the objects. You can use either of the contrastive words, but not both. You should think about more such attributes and associated words and use them in your question.\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\nContext Word: camp." }, { "from": "gpt", "value": "At camp, they blew a bugle for breakfast and a whistle for lunch, and since they blew the _ we knew it was lunch." } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given a text from a social media post. Your task is to classify the given post into two categories: 1) yes if the given post is sexually offensive, 2) no, otherwise. Emphasis on sexually offensive or any lewd reference. Generate label 'no' for offensive posts that do not reference sexually explicit content. Warning: the examples and instances may contain offensive language.\n\nI was accused of stealing panties I had returned it after i put my cum.\nOutput:" }, { "from": "gpt", "value": "Yes" } ]
[ { "from": "human", "value": "Teacher: 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\".\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nAbstract: 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\nReason: Title is appropriate for the given abstract because the focus of this abstract is cerebral white matter assesment.\n\nNow, solve this instance: Abstract: Human cytomegalovirus (HCMV) expresses several homologues of human interleukin 10 (hIL-10) possessing immunomodulatory properties which may promote viral infection by modulating the function of myeloid cells. We examined the phenotype and phagocytic capability of human monocytes exposed to hIL-10, an HCMV-encoded hIL-10 homologue expressed during the productive phase of infection (cmvIL-10), and a differentially spliced form of cmvIL-10 expressed during latent and productive phases of infection, (LAcmvIL-10). hIL-10 and cmvIL-10 upregulated expression of Fcgamma receptors, stimulated phagocytosis of IgG-opsonised erythrocytes and decreased MHC class II (HLA-DR) expression on purified monocytes within 24 h. In contrast, LAcmvIL-10 decreased HLA-DR expression at later times (48 h and 72 h) but did not increase Fcgamma receptor expression. We conclude that cmvIL-10 promotes differentiation of monocytes towards a pro-phagocytic phenotype and that LAcmvIL-10 does not affect monocytes by the same mechanism as cmvIL-10. The significance of these properties to cytomegalovirus pathogenesis is discussed.. Title: Enhanced monocyte Fc phagocytosis by a homologue of interleukin-10 encoded by human cytomegalovirus.\nStudent:" }, { "from": "gpt", "value": "yes" } ]
[ { "from": "human", "value": "Detailed Instructions: You're given a sentence and your task is to classify whether the sentence is acceptable or not. Any sentence which is grammatically correct, has a naturalistic text, is written by a native speaker and which minimizes superfluous content is acceptable, otherwise unacceptable. If the sentence is acceptable then write \"acceptable\", otherwise \"unacceptable\".\nProblem:I put the book to Sally.\nSolution:" }, { "from": "gpt", "value": "unacceptable" } ]
[ { "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 generate a natural language interpretation of the given command. \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 argument 1 is greater/less than argument 2 \n 12. diff: returns the difference between two arguments \n 13. filter eq/not eq: returns the subview whose values under the header column is equal/not equal to argument 3 \n 14. filter greater/less: returns the subview whose values under the header column is greater/less than argument 3 \n 15. filter greater eq /less eq: returns the subview whose values under the header column is greater/less or equal than argument 3 \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 argument 3 \n 18. all greater/less: returns whether all the values under the header column are greater/less than argument 3 \n 19. all greater eq/less eq: returns whether all the values under the header column are greater/less or equal to argument 3 \n 20. most eq/not eq: returns whether most of the values under the header column are equal/not equal to argument 3 \n 21. most greater/less: returns whether most of the values under the header column are greater/less than argument 3 \n 22. most greater eq/less eq: returns whether most of the values under the header column are greater/less or equal to argument 3\n\nEx Input:\neq { count { filter_eq { all_rows ; nationality ; germany } } ; 2 } = true\n\nEx Output:\nselect the rows whose nationality record fuzzily matches to germany . the number of such rows is 2 .\n\n\nEx Input:\neq { hop { argmin { all_rows ; year born } ; player } ; goran jagodnik } = true\n\nEx Output:\nselect the row whose year born record of all rows is minimum . the player record of this row is goran jagodnik .\n\n\nEx Input:\neq { hop { nth_argmax { all_rows ; location attendance ; 2 } ; date } ; january 12 } = true\n\nEx Output:\n" }, { "from": "gpt", "value": "select the row whose location attendance record of all rows is 2nd maximum . the date record of this row is january 12 .\n\n\n" } ]
[ { "from": "human", "value": "Teacher:In this task, you need to count the number of times the given letter appears in the given sentence.\nTeacher: Now, understand the problem? Solve this instance: Sentence: 'there is a male surfer in the ocean riding a wave'. Find frequency of the letter 'r'\nStudent:" }, { "from": "gpt", "value": "4" } ]
[ { "from": "human", "value": "In this task you will be given an arithmetic operation and you have to find its answer. The symbols of operators '+' and '-' has been swapped i.e you need to perform subtraction when you see a '+' symbol and addition in case of '-' symbol.\n\nQ: 1673 - 3914 + 8016 + 5937 - 8915 + 4818\n\nA: -4269\n**\nQ: 6178 - 1637 - 8197 - 6437 + 4591 - 6995 + 3562 + 9474\n\nA: 11817\n\nQ: 9191 - 18 + 3055 + 1188 - 9309 - 1293\n\nA:" }, { "from": "gpt", "value": "15568\n**\n" } ]
[ { "from": "human", "value": "Instructions: In this task you are given a statement and an explanation giving you further knowledge about an entity in the statement. You must judge whether the statement is true or false based on the explanation. Label an instance as \"True\" if the explanation confirms the statement or doesn't disprove it. Label an instance as \"False\" if the explanation disproves the statement. The statement and explanation are separated by a newline character.\nInput: Lionel Richie raps in his music.\nLionel Richie does not perform rap music\nOutput:" }, { "from": "gpt", "value": "False" } ]
[ { "from": "human", "value": "In this task, you're given a review from Amazon. Your task is to generate a 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.\n\nI thought I was getting old cut up t-shirts. Half the box was T-shirts and the other half was old pillow cases which are not good shop rags and the pillow cases were still one piece.\n2\n\nDon't waste your money to buy this, the mouse can't leave the mouse pad for 10 seconds, otherwise it will automatically power off, and my mouse pad rgb broken within three months.\n1\n\nShipped out on time and arrived early! Very neat package and perfect invoice/product. Product package was sealed and when opened, product was fresh. Good Quality product!!\n" }, { "from": "gpt", "value": "5\n\n" } ]
[ { "from": "human", "value": "The task is to generate the correct answer for a given math problem.\n\n[EX Q]: Problem: one half of a two digit number exceeds its one third by 7 . what is the sum of the digits of the number ?\n[EX A]: e ) 1\n\n[EX Q]: Problem: for any positive integer n , the sum of the first n positive integers equals n ( n + 1 ) / 2 . what is the sum of odd all the integers between 10 and 100 ?\n[EX A]: 2475\n\n[EX Q]: Problem: a cycle is bought for rs . 900 and sold for rs . 1170 , find the gain percent ?\n[EX A]:" }, { "from": "gpt", "value": "30 %\n\n" } ]
[ { "from": "human", "value": "Teacher:In this task, you are given a dialogue from a conversation between an agent and a customer. Your task is to determine the speaker of the dialogue. Answer with \"agent\" or \"customer\".\nTeacher: Now, understand the problem? Solve this instance: OK, Thanks for your information.\nStudent:" }, { "from": "gpt", "value": "customer" } ]
[ { "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: Smelly Fridge. Sentence 1: John was at home. Sentence 2: He was thirsty. Sentence 3: He opened the fridge to see what he had to drink. Sentence 4: When the fridge was opened a very bad smell came out. Choices: a. John quickly cleaned the fridge. b. Old Red was a fun animal to play with.\nSolution:" }, { "from": "gpt", "value": "a" } ]
[ { "from": "human", "value": "In this task, you are given an input list A. You need to convert all the alphabets in the list with a number representing their position in the English alphabet. E.g., replace A by 1, B by 2, a by 1, b by 2, and so on.\nQ: ['A', 'C', 'S', '7301']\nA: " }, { "from": "gpt", "value": "1, 3, 19, 7301" } ]
[ { "from": "human", "value": "Q: Based on the given question and tppic, give an answer. The answer is available on on the internet. The questions are mostly centered around a single named entity.\nconcept: Michael Jackson question: what was the cause of death of michael jackson?\nA:" }, { "from": "gpt", "value": "['Homicide', 'Cardiac arrest']" } ]
[ { "from": "human", "value": "Instructions: You are given a question. You need to detect which category better describes the question. A question belongs to the description category if it asks about description and abstract concepts. Entity questions are about entities such as animals, colors, sports, etc. Abbreviation questions ask about abbreviations and expressions abbreviated. Questions regarding human beings, description of a person, and a group or organization of persons are categorized as Human. Quantity questions are asking about numeric values and Location questions ask about locations, cities, and countries. Answer with \"Description\", \"Entity\", \"Abbreviation\", \"Person\", \"Quantity\", and \"Location\".\nInput: What is a Devo hat ?\nOutput:" }, { "from": "gpt", "value": "Description" } ]
[ { "from": "human", "value": "In this task, you will be shown a short story with a beginning, two potential middles, and an ending. Your job is to choose the middle statement that makes the story coherent / plausible by writing \"1\" or \"2\" in the output. If both sentences are plausible, pick the one that makes most sense.\n\nLet me give you an example: Beginning: Butch had a really old computer. Middle 1: Butch decided to order a new computer online. Middle 2: Butch noticed that a storm was approaching to his town. Ending: It arrived and Butch was much happier.\nThe answer to this example can be: 1\nHere is why: People generally don't feel happy about natural disasters like storms. Therefore, we choose 1 in this case.\n\nOK. solve this:\nBeginning: Amy and Charles were going shopping for an engagement ring. Middle 1: Amy got a ring she loved. Middle 2: Amy got a rhino that she loved. Ending: Amy started at her new ring all the way home.\nAnswer:" }, { "from": "gpt", "value": "1" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you are given two lists A,B. Find the longest common subsequence in the lists A and B.\n\n[9469, 8117, 'I', 1049, 6153, 'L', 1465, 9935, '857', '4275', 'O', '3819', '4873', 'p', '8971', 'E', '3587', '4115', '1407', '5177', 'b', 'T', '111', 'z', 'z', '7879', 't', 'h', 'G', 'M', 'r', 6565, 'g', 'A'], [8843, 'R', 1387, 'U', '857', '4275', 'O', '3819', '4873', 'p', '8971', 'E', '3587', '4115', '1407', '5177', 'b', 'T', '111', 'z', 'z', '7879', 't', 'd', 'X', 'R', 'A', 'P', 3527, 'D', 9207, 8179, 'G']\n" }, { "from": "gpt", "value": "857, 4275, O, 3819, 4873, p, 8971, E, 3587, 4115, 1407, 5177, b, T, 111, z, z, 7879, t" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you will be presented with a question about part-of-speech tag of a word in the question. You should write an implausible POS tag to the question. Even though there exist multiple wrong answers, we only need a single wrong answer. Here is the Alphabetical list of part-of-speech tags used in this task: CC: Coordinating conjunction, CD: Cardinal number, DT: Determiner, EX: Existential there, FW: Foreign word, IN: Preposition or subordinating conjunction, JJ: Adjective, JJR: Adjective, comparative, JJS: Adjective, superlative, LS: List item marker, MD: Modal, NN: Noun, singular or mass, NNS: Noun, plural, NNP: Proper noun, singular, NNPS: Proper noun, plural, PDT: Predeterminer, POS: Possessive ending, PRP: Personal pronoun, PRP$: Possessive pronoun, RB: Adverb, RBR: Adverb, comparative, RBS: Adverb, superlative, RP: Particle, SYM: Symbol, TO: to, UH: Interjection, VB: Verb, base form, VBD: Verb, past tense, VBG: Verb, gerund or present participle, VBN: Verb, past participle, VBP: Verb, non-3rd person singular present, VBZ: Verb, 3rd person singular present, WDT: Wh-determiner, WP: Wh-pronoun, WP$: Possessive wh-pronoun, WRB: Wh-adverb\nQ: What is the part-of-speech tag of the word \"that\" in the following question: The America East Men 's Basketball Tournament in which the winning team clinched the title against a team it had lost to in the tournament just three years prior took place in an arena that seats how many ?\nA:" }, { "from": "gpt", "value": "NNP" } ]
[ { "from": "human", "value": "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.\n\nQ: Given Relationship: 'be borough of', Sentence: 'In between his sea voyages , Kerouac stayed in New York City with friends from Fordham University in The Bronx . He lived with his parents in the Ozone Park neighborhood of the New York City borough of Queens after he was discharged from the U.S. Navy in 1943 .'\n\nA: borough\n**\nQ: Given Relationship: 'be found by', Sentence: 'The Salvation Army was founded by William Booth , a former Methodist , and derives some of its theology from Methodism .'\n\nA: founded\n\nQ: Given Relationship: 'be home to', Sentence: 'Mumbai is the home of Bollywood movies which entertain the world .'\n\nA:" }, { "from": "gpt", "value": "home\n**\n" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nThis task involves creating answers to complex questions, from a given passage. Answering these questions, typically involve understanding multiple sentences. Make sure that your answer has the same type as the \"answer type\" mentioned in input. The provided \"answer type\" can be of any of the following types: \"span\", \"date\", \"number\". A \"span\" answer is a continuous phrase taken directly from the passage or question. You can directly copy-paste the text from the passage or the question for span type answers. If you find multiple spans, please add them all as a comma separated list. Please restrict each span to five words. A \"number\" type answer can include a digit specifying an actual value. For \"date\" type answers, use DD MM YYYY format e.g. 11 Jan 1992. If full date is not available in the passage you can write partial date such as 1992 or Jan 1992. If you find multiple spans, please add them all as a comma separated list. Please restrict each span to five words.\n\nPassage: The Giants' winning streak came to an end in San Francisco but they once again had the game in doubt into the final minutes. Field goals comprised the first half scoring, with Lawrence Tynes hitting two and the 49ers' David Akers recording three. The Giants took their only lead in the third quarter as Eli Manning found Mario Manningham for 13 yards to complete an 84-yard drive. The 49ers recorded two touchdowns on a pass to Vernon Davis and a run by Kendall Hunter, while Manning hit Hakeem Nicks for a 32-yard touchdown late in the game. New York received the ball late in the game and drove inside the 49ers' red zone, but Manning's last pass was deflected at the line of scrimmage to preserve the San Francisco win. Manning threw for 311 yards and two touchdowns but also recorded two interceptions, while Alex Smith threw for 242 and the touchdown pass to Davis. Brandon Jacobs rushed for 55 yards to lead the runners while Victor Cruz's 84 yards was tops for the receivers. \nQuestion: How many more yards did Cruz gain compared to Jacobs? \nAnswer type: Number \nOutput:" }, { "from": "gpt", "value": "29." } ]
[ { "from": "human", "value": "You are given a sentence in English. Your job is to translate the English sentence into Italian.\n\nAnd it'll be on these questions: where did I come from? Why am I here? Where am I going?" }, { "from": "gpt", "value": "E sara 'su queste poche domande: Da dove vengo? Perche' sono qui? Dove andro '?" } ]
[ { "from": "human", "value": "Q: 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.\nContext : Brad Larsen was born in Nakusp, British Columbia, but grew up in Vernon, British Columbia. \nQuestion : What team is Brad Larsen associated with?\nA:" }, { "from": "gpt", "value": "drafted by" } ]
[ { "from": "human", "value": "Part 1. Definition\nIn 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.\nPart 2. Example\n['238', 'h', '92', 'U', '2799']\nAnswer: h, U, 238, 92, 2799\nExplanation: Here, the alphabetical elements in order in the list are 'h' and 'U', and the numerical elements in order in the input list are '238', '92' and '2799'. Keeping all the alphabetical elements at the start of the list, and the numerical elements at the end of the list in the same order gives 'h, U, 238, 92, 2799'.\nPart 3. Exercise\n['4535', '3537', 'r', 'e', 'A']\nAnswer:" }, { "from": "gpt", "value": "r, e, A, 4535, 3537" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn 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.\nExample: 3, 7, ['A', '23', '7413', '6933', '3369', '807', 'M', '456']\nOutput: 18522\nHere, the numbers from 3rd to 7th position are '7413', '6933', '3369', and '807', hence their sum (7413+6933+3369+807) is 18522.\n\nNew input case for you: 11, 17, ['a', 'S', 'M', '1827', 'F', '225', '7865', 'v', '5013', '3865', 'w', 'N', 'e', 't', '9559', 'W', '3973', '7521', '9489', '6237', '3989', 'q', 'K', 'W']\nOutput:" }, { "from": "gpt", "value": "13532" } ]
[ { "from": "human", "value": "Detailed Instructions: Based on the given context, craft a common-sense question, especially those that are LONG, INTERESTING, and COMPLEX. The goal is to write questions that are easy for humans and hard for AI machines! To create such questions, here are some suggestions: A. What may (or may not) be the plausible reason for an event? B. What may (or may not) happen before (or after, or during) an event? C. What may (or may not) be a plausible fact about someone (or something)? D. What may (or may not) happen if an event happens (or did not happen)? You can also create other types of questions. DO NOT make your question answerable without looking at the context, or question of which the correct answer can be directly extracted from the context. DO NOT ask a question that requires very specialized knowledge that is not common sense. DO NOT ask too simple or too short questions. Your question must be related to the context and answerable with common sense. Try to add more variations and complexity to the questions.\nProblem:Context: But of course . Invariably , I am tempted to request a kiss , but the rare lip - to - lip contact she makes me crave often comes when I least expect it and never when I outright demand it . She is a frustrating lover who operates on a whim , most affectionate when least solicited . CK is a small woman , and that too is part of her charm .\nSolution:" }, { "from": "gpt", "value": "What may happen if this continues for a few more years ?" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. Craft one correct answer to the question given in input. To make it more interesting, try to use non-stereotypical language if possible. Make sure your correct answer is reasonably long, consistent with the context, and requires common sense (instead of explicit extraction from the context.) In your answer, use as few words as possible from the given context. Use a response that is uncommon/non-stereotypical, so that it is less predictable. To be less repetitive, please vary your language for each question.\n\nContext: Bake in the preheated oven for 35 minutes , or until a toothpick inserted into the center of the cake comes out clean . Cool for 10 minutes on a cooling rack , then unmold cake . Cool completely before serving . Store in an airtight container once cooled . \nQuestion: What type of cuisine is the narrator teaching ?\n" }, { "from": "gpt", "value": "They are teaching baking ." } ]
[ { "from": "human", "value": "Detailed Instructions: You are given an original reference as well as a system reference. Your task is to judge the informativeness of the system reference. If the utterance provides all the useful information from the meaning representation output 1, else output 0.\nProblem:System Reference: he harbor court hotel c a kimpton hotel is located near soma.\nOriginal Reference: harbor court hotel c a kimpton hotel which is near soma.\nSolution:" }, { "from": "gpt", "value": "0" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given a context passage, followed by a question that needs to be answered. Based on the paragraph, you must write unambiguous answers to the questions and your answer must refer to a specific phrase from the paragraph. If multiple answers seem to exist, write the answer that is the most plausible.\nProblem:Kendall ordered flowers from Robin's flower shop across town. \nQuestion: Why did Robin do this?\nSolution:" }, { "from": "gpt", "value": "fulfill the request" } ]
[ { "from": "human", "value": "Q: 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.\n[['The Mill', 'eatType', 'pub'], ['The Mill', 'food', 'Italian'], ['The Mill', 'area', 'riverside']]\nA:" }, { "from": "gpt", "value": "The Mill is a high-end Italian pub in riverside." } ]
[ { "from": "human", "value": "In this task, you will be shown a sentence, and you should determine whether it is overruling or non-overruling. In law, an overruling sentence is a statement that nullifies a previous case decision as a precedent by a constitutionally valid statute or a decision by the same or higher ranking court which establishes a different rule on the point of law involved. Classify your answers into overruling or non-overruling\n\nschulte v. venture stores, inc., 832 s.w.2d 13 (mo.app. 1992), and hoskin v. younger cemetery corp., 838 s.w.2d 476 (mo.app. 1992), to the extent that they conflict, are overruled." }, { "from": "gpt", "value": "overruling" } ]
[ { "from": "human", "value": "Detailed Instructions: 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'.\nProblem:21 Nov 1977 occured before 01 June 1992 but after 15 December 1992\nSolution:" }, { "from": "gpt", "value": "False" } ]
[ { "from": "human", "value": "Given a math word problem, answer the following question. You might need to apply addition or subtraction mathematical operators on the numbers embedded in the text to answer the question and then only report the final numerical answer.\n\nLet me give you an example: robin bought 11 sodas for her and her friends . if they only drank 3 of them how many extras did she have ?\nThe answer to this example can be: 8\nHere is why: Extra sodas is total - drank = 11-3 = 8\n\nOK. solve this:\nmaria took 16 fish out of her fish tank . now there are 3 fish in the tank . how many fish were in the tank to start with ?\nAnswer:" }, { "from": "gpt", "value": "19" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to write a single word that describes the genre that the two sentences belong to, such as face-to-face, government, letters, 9/11, slate, telephone, travel, verbatim, oup, fiction.\n\nSentence 1: He had planned it this way no demands, no claims on a stranger, freedom to make the decision of when or how he would see his father; that was the only path he could take. Sentence 2: He had not seen his father since they were separated on the boat.\n" }, { "from": "gpt", "value": "fiction" } ]
[ { "from": "human", "value": "Teacher: In this task, you are given a passage and a question regarding that passage. You must determine whether or not the question is answerable from the given passage. If a question is answerable, output should be 'True', otherwise 'False'. You must not consider any other information that is not provided in the passage while labelling True or False.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nPassage: Madonna released the Material Girl clothing line, which she designed with her daughter, Lourdes. The 1980s inspired clothing line, borrowed from Madonna's punk-girl style when she rose to fame in the 1980s, was released under the Macy's label. Madonna also opened a series of fitness centers around the world named Hard Candy Fitness. In November 2011, Madonna and MG Icon announced the release of a second fashion brand called Truth or Dare by Madonna to include footwear, underclothing, and accessories. She also directed her second feature film, W.E., a biographic about the affair between King Edward VIII and Wallis Simpson; it was co-written with Alek Keshishian. Critical and commercial response to the film was negative. Madonna contributed the ballad \"Masterpiece\" for the film's soundtrack, which won her a Golden Globe Award for Best Original Song. Question: Material Girl clothing line is released under which brand?\nSolution: True\nReason: The answer to given question is 'Macy's', which can be determined from the second sentence of the paragraph \"The 1980s inspired clothing line, borrowed from Madonna's punk-girl style when she rose to fame in the 1980s, was released under the Macy's label\". Since this question is answerable, the output is True.\n\nNow, solve this instance: Passage: Connection-oriented transmission requires a setup phase in each involved node before any packet is transferred to establish the parameters of communication. The packets include a connection identifier rather than address information and are negotiated between endpoints so that they are delivered in order and with error checking. Address information is only transferred to each node during the connection set-up phase, when the route to the destination is discovered and an entry is added to the switching table in each network node through which the connection passes. The signaling protocols used allow the application to specify its requirements and discover link parameters. Acceptable values for service parameters may be negotiated. Routing a packet requires the node to look up the connection id in a table. The packet header can be small, as it only needs to contain this code and any information, such as length, timestamp, or sequence number, which is different for different packets. Question: How is error checking involved in delivery? \nStudent:" }, { "from": "gpt", "value": "False" } ]
[ { "from": "human", "value": "Part 1. Definition\nIn this task, answer 'Yes' if the frequency of the given word in the two sentences is equal, else answer 'No'.\nPart 2. Example\nSentence1: '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?\nAnswer: No\nExplanation: Frequency of the word 'beside' in Sentence1 is 1 but 0 in Sentence2. So, the answer is 'No'\nPart 3. Exercise\nSentence1: 'two baseball players warming up before a game', Sentence2: 'a man that is holding a cell phone'. Is the frequency of the word 'players' in two sentences equal?\nAnswer:" }, { "from": "gpt", "value": "No" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you need to replace a letter in the sentence with another given letter.\nQ: Sentence: 'living room chair and ottoman with dining area in background'. Replace the letter 't' with 'a' in the sentence.\nA:" }, { "from": "gpt", "value": "living room chair and oaaoman wiah dining area in background" } ]
[ { "from": "human", "value": "Teacher: An answer is given. Generate a question for which the given answer is either a direct or partial answer.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nAnswer: victoria woodhull\nSolution: who was the first women to run for presidency in the us?\nReason: The given answer directly answers the generated question\n\nNow, solve this instance: Answer: brain tumor\nStudent:" }, { "from": "gpt", "value": "what were george harrisons illnesses?" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given a question, along with a context passage which has extra information available on certain terms mentioned in it. Your job is to determine which sentence(s) from the passage can be used to search for further information needed to answer the question.\nQ: Question: In which state did Fischell work full time in a lab for 25 years? Passage:Robert Fischell (born 1929) is a physicist, prolific inventor, and holder of more than 200 U.S. and foreign medical patents. His inventions have led to the creation of several biotechnology companies. He worked at the Johns Hopkins University Applied Physics Laboratory full-time for 25 years, and part-time for an additional 13 years. He contributed to APL's satellite navigation work, and later developed a rechargeable implantable pacemaker that could be programmed with radiowaves, (Pacesetter Systems purchased by Siemens, now the CRM division of St. Jude Medical). He and his team at Hopkins also helped miniaturize the implantable cardiac defibrillator. Mr. Fischell went on to invent the implantable insulin pump (MiniMed, spun off from Pacesetter Systems in 1985), numerous coronary stents used to open clogged arteries (IsoStent merged with Cordis, in turn purchased by Johnson & Johnson), and two extraordinary feedback systems that provide early warning of epileptic seizures (NeuroPace) and heart attacks (Angel Medical Systems). Fischell recently donated $30 million to the University of Maryland College Park Foundation to establish a bioengineering department and an institute for biomedical devices at the A. James Clark School of Engineering.\n\nA:" }, { "from": "gpt", "value": "He worked at the Johns Hopkins University Applied Physics Laboratory full-time for 25 years, and part-time for an additional 13 years" } ]
[ { "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: obscene and non-obscene. A comment is obscene if it is considered offensive to the public sense of decency, for example because it too obviously relates to sex or contains language regarded as taboo in polite usage.\nInput: Comment: Trump voters love the fact that his sense of morality is no better than their own. They wish they could get away with grading women by the p***y too.\nOutput:" }, { "from": "gpt", "value": "Obscene" } ]
[ { "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, and three sentences as choices. Your job is to determine which sentence clearly disagrees with the statement. Indicate your answer as '1', '2', or '3' corresponding to the choice number of the selected sentence.\n\nStatement: He thought the facts had been misrepresented. Choices: 1. He wasn't sure if the facts were really facts. 2. He suspected that the facts hadn't been presented clearly. 3. The facts were represented concisely and truthfully.\nOutput:" }, { "from": "gpt", "value": "3" } ]
[ { "from": "human", "value": "In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to 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\n[Q]: 15, 21, ['w', 'R', '9247', '5745', '5397', 'U', 'R', 'e', '8067', 'e', '2851', 'O', 'F', '4705', '5393', 'q', 'b', 'J', '211', '4319', 'o', 'h', 'Z', '4423', 'j', '2691', 'U']\n[A]: 9923\n\n\n[Q]: 7, 12, ['273', 'h', '2433', '7155', '731', '5459', 'q', 'G', 'i', 'l', '3981', 'W', 'V', '4999', '8191', 'K', '8393', '9255']\n[A]: 3981\n\n\n[Q]: 1, 11, ['G', 'o', 'U', 'Q', 'J', '6495', 'z', '2903', '3557', 'p', '7351', 'v', 'q', '1591', '245', 'f']\n[A]:" }, { "from": "gpt", "value": "20306\n\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: Given a pair of words, deduce the type of relationship between them. The various types of relations are: 'Entails, HasProperty, Synonym, Antonym, HasA, MemberOf, PartOf, MadeOf, IsA'. Let's denote the first word by X and the second word by Y. An 'IsA' relation holds when 'X is a kind of Y'. An 'Antonym' relation holds when 'X can be used as the opposite of Y'. A 'Synonym' relation applies when 'X can be used in place of Y, without changing the meaning'. A 'PartOf' relation holds when 'X is a part of Y'. A 'MemberOf' relation holds when 'X is a member of Y'. A 'MadeOf' relation holds when 'X is made of Y'. An 'Entailment' relation holds when 'If X is true, then Y is true as well'. A 'HasA' relation holds when 'X can have or contain Y'. A 'HasProperty' relation holds when 'Y is to specify X'.\nProblem:X: benevolent, Y: evil\nSolution:" }, { "from": "gpt", "value": "Antonym" } ]
[ { "from": "human", "value": "Given a sentence in Italian, generate a new Italian sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.\nQ: Se si vuole scalare un metro allora si dovrebbe avere nastro appropriato.\nA: " }, { "from": "gpt", "value": "Se si desidera scalare un punto allora si dovrebbe avere la navigazione appropriata." } ]
[ { "from": "human", "value": "In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to write a single word that describes the genre that the two sentences belong to, such as face-to-face, government, letters, 9/11, slate, telephone, travel, verbatim, oup, fiction.\n\nSentence 1: The future's bright. Sentence 2: I am optimistic about life.\nslate\n\nSentence 1: The sport was a new one to him. Sentence 2: He knows lots about the sport.\nfiction\n\nSentence 1: particularly if you're hungry Sentence 2: I am full.\n" }, { "from": "gpt", "value": "telephone\n\n" } ]
[ { "from": "human", "value": "In this task you will be given a string and you should find the longest substring that is a palindrome. A palindrome is a string that is the same backwards as it is forwards. If the shortest possible palindrome is length 1 you should return the first character.\nOne example: gocogccocco\nSolution is here: gocog\nExplanation: The substring 'gocog' is the longest possible substring that is also a palindrome. So this is a good example.\n\nNow, solve this: eeeggegpgpgeggg\nSolution:" }, { "from": "gpt", "value": "ggegpgpgegg" } ]
[ { "from": "human", "value": "Detailed Instructions: Given an trivia question precisely answer the question with a word/phrase/name. External resources such as Wikipedia could be used to obtain the facts.\nSee one example below:\nProblem: Which writer rode Devon Loch in the 1956 Grand National?\nSolution: dick francis\nExplanation: The answer is precise and accurately answers the question based on a fact. This is a good example\n\nProblem: What is the name of the futuristic nation in the 2012 film 'The Hunger Games'?\nSolution:" }, { "from": "gpt", "value": "the hunger games universe" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task you will be given a list of integers. A list contains numbers separated by a comma. You need to round every integer to the closest power of 2. A power of 2 is a number in the form '2^n', it is a number that is the result of multiplying by 2 n times. The following are all powers of 2, '2, 4, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096'. If an integer is exactly in equally far from two different powers of 2 then you should output the larger power of 2. The output should be a list of integers that is the result of rounding each integer int the input list to the closest power of 2. The output should include a '[' to denote the start of the output list and ']' to denote the end of the output list.\nQ: [108, 255, 1192, 4272, 14]\nA:" }, { "from": "gpt", "value": "[128, 256, 1024, 4096, 16]" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nBased on the given question and tppic, give an answer. The answer is available on on the internet. The questions are mostly centered around a single named entity.\nExample: concept: Selena Gomez question: what city was selena gomez born in?\nOutput: New York City\nThe answer is correct based on the information available on the web about Selena Gomez.\n\nNew input case for you: concept: Alani Vasquez question: where does lala anthony live?\nOutput:" }, { "from": "gpt", "value": "['Brooklyn']" } ]
[ { "from": "human", "value": "You are given an amazon food product review and its polarity (positive or negative). Your task is to answer \"True\" if the specified sentence and its polarity match; otherwise, answer \"False\".\n--------\nQuestion: This product serves me well as a source of electrolytes during and after a long run or bike ride. I have tried all of the flavors but really do like the grapefruit flavor... no after-taste and I actually like the slight carbonation. I use other Hammer products and really like their whole product line. \n Polarity: Positive\n\nAnswer: True\n\n\nQuestion: I have searched for hot chocolate for my Keurig, but couldn't find any that were economical to purchase. I found this at a decent price, and was I glad! My husband absolutely loves this hot chocolate and says it reminds him of his childhood. Try it - you'll like it! \n Polarity: Negative\n\nAnswer: False\n\n\nQuestion: These creamers come in 4 packs of 25. I have taken one to work and opened one for home so far, and haven't found a single broken or leaking creamer yet. I usually have way too much cream and sugar in my coffee, but with these it is easy for me to cut down on the sweetness because I won't allow myself more than 2 creamers per cup. I think this is definitely the best option for buying creamers from Amazon since all the other listings have a lot of complaints about creamers breaking in shipping! \n Polarity: Positive\n\nAnswer:" }, { "from": "gpt", "value": "True\n\n\n" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you're expected to write answers to questions involving multiple references to the same entity. The answer to the question should be unambiguous and a phrase in the paragraph. Most questions can have only one correct answer.\n\nPassage: Eric O'Neill is a young FBI employee assigned to work undercover as a clerk to Robert Hanssen, a senior agent he is told is suspected of being a sexual deviant. Hanssen has been recalled from a detail post at the State Department to FBI headquarters ostensibly to head up a new division specializing in Information Assurance.\nInitially, Hanssen insists on a strict formality between the two men. He frequently rails against the bureaucracy of the FBI and complains that only those who regularly \"shoot guns\" are considered for senior positions instead of those, like himself, who are involved in vital national security matters. He calls the bureau's information technology systems antiquated and laments the lack of coordination and information exchange with other intelligence agencies.\nEventually, Hanssen becomes a friend and mentor to O'Neill and takes a personal interest in him and his wife Juliana, who is suspicious of Hanssen and resents his intrusions. A devout Catholic who is also a member of Opus Dei, Hanssen urges O'Neill, a lapsed Catholic, and his secular East German-born wife to become active churchgoers. \nQuestion: What is the full name of the member of Opus Dei?\nOutput:" }, { "from": "gpt", "value": "Robert Hanssen." } ]
[ { "from": "human", "value": "In this task, you're given a statement and three sentences as choices. Your job is to determine the neutral choice based on your inference from the statement and your commonsense knowledge. The neutral choice is a sentence that neither agrees nor disagrees with the statement. Indicate your answer as '1', '2', or '3', corresponding to the choice number of the selected sentence. If sentence X agrees with sentence Y, one's correctness follows from the other one. If sentence X disagrees with sentence Y, they can not be correct at the same time.\nExample: Statement: Next to the MGM Grand you will find M and M World, four stories of merchandise and memorabilia dedicated to the candy that doesn't melt in your hand. Choices: 1. The candy has many fans who love its attractions. 2. There's four stories of memorabilia dedicated to a candy. 3. That particular candy melts and becomes difficult to eat.\nExample solution: 1\nExample explanation: The candy may or may not be popular and the first choice is correct. Based on the statement, candy doesn't melt and there's four stories of memorabilia dedicated to a candy. So the second choice agrees with the statement and the third choice disagrees with the statement.\n\nProblem: Statement: Participants also believed that a challenge facing the new PCAOB will be dealing with the complex relationship between federal and state governments involved in regulating the accounting profession. Choices: 1. Participants also believed that the new PCAOB needs to deal with the challenge of regulating interest rates in banks. 2. There is a complex relationship between federal and state governments pertaining to regulating the accounting profession, and participants believed that this is a challenge presented to the new PCAOB. 3. Participants did not believe that the relationship between federal and state governments involved in regulating the accounting profession was a challenge for the new PCAOB.\n" }, { "from": "gpt", "value": "Solution: 1" } ]
[ { "from": "human", "value": "An answer is given. Generate a question for which the given answer is either a direct or partial answer.\nOne example: Answer: victoria woodhull\nSolution is here: who was the first women to run for presidency in the us?\nExplanation: The given answer directly answers the generated question\n\nNow, solve this: Answer: bangalore\nSolution:" }, { "from": "gpt", "value": "top 10 largest cities in india based on land area?" } ]
[ { "from": "human", "value": "In this task you are given a sentence. You must judge whether the object of the main clause is singular(like: apple) or plural(like: apartments). Label the instances as \"Singular\" or \"Plural\" based on your judgment.\n\nExample input: They both let out relieved breaths at the doctor's words.\nExample output: Plural\nExample explanation: \"relieved breaths\" is the object of the sentence which is plural.\nQ: \" I felt the blast.\nA:" }, { "from": "gpt", "value": "Singular" } ]
[ { "from": "human", "value": "In this task, you are given two natural language statements with similar wording. You must choose the statement that makes less sense based on common sense knowledge. A '\n' separates the statements. Use \"first\" or \"second\" to indicate which sentence makes less sense.\n\nLet me give you an example: A mosquito stings me\nI sting a mosquito\nThe answer to this example can be: second\nHere is why: The second statement doesn't make sense.\n\nOK. solve this:\nHe cut the grass with a lawn mower.\nHe cut the grass with a hammer.\nAnswer:" }, { "from": "gpt", "value": "second" } ]
[ { "from": "human", "value": "Definition: Classify the given tweet into the three categories: (1) 'Hate Speech', (2) 'Offensive' and (3) 'Neither'. 'Hate Speech' is kind of a threating statement or sometimes include call for violence while 'offensive' statement just offensds someone. 'Neither' is when it doesn't fall into Hate Speech or Offensive category.\nInput: I couldn't press send. That tweet about anchor babies was even too raw for me.\nOutput:" }, { "from": "gpt", "value": "Neither" } ]
[ { "from": "human", "value": "In this task, you are given inputs i and A, where i is an integer and A is a list. You need to list all the elements of A preceding the last i elements. i will always have a value less than the length of A.\nQ: 2, ['G', '6093', '1095', '6111', 't', '9727', 'i', 'v', '9097']\nA: " }, { "from": "gpt", "value": "G, 6093, 1095, 6111, t, 9727, i" } ]
[ { "from": "human", "value": "Definition: You are given a short text as a title. Your task is to generate a poem as output that is related to the given title and should feel like written by kids. The output should be a run-on sentence (two or more complete sentences connected without any punctuation). The poem should not be too long or too complex, because it should feel like it is written by younger person without high level of literature education.\nInput: The Blue Stork\nOutput:" }, { "from": "gpt", "value": "when i awake one morning a stork be on my head i ask" } ]
[ { "from": "human", "value": "Definition: In this task, you're given a four sentences of story written in natural language. Your job is to complete end part of the story by predicting appropriate last sentence which is coherent with the given sentences.\nInput: Sentence1: Michael and I had a staring contest. Sentence2: It was a battle that lasted thirty four seconds. Sentence3: I finally could not hold it and I blinked first. Sentence4: Michael always beats me but I am competitive.\nOutput:" }, { "from": "gpt", "value": "I practice by staring into a mirror so I can beat Michael." } ]
[ { "from": "human", "value": "instruction:\nIn this task, you are given inputs i and A, where i is an integer and A is a list. You need to list all the elements of A after the first i elements. i will always have a value less than the length of A.\nquestion:\n3, ['995', 'I', 'w', '6787', 'z', '8049', '6019', 'g', 'e', '6825', '4289']\nanswer:\n6787, z, 8049, 6019, g, e, 6825, 4289\n\n\nquestion:\n1, ['D', '4349', 'X', 'h', '6275', '5247', 'n', '3245', '1995', 'Z', 'I', '5837', '8053', 'v', '7223', '1935', 'D', 'f', 'o', 'G', 's', '1233', 'Z', 'm', 'v', 'G']\nanswer:\n4349, X, h, 6275, 5247, n, 3245, 1995, Z, I, 5837, 8053, v, 7223, 1935, D, f, o, G, s, 1233, Z, m, v, G\n\n\nquestion:\n4, ['1617', '8359', '9881', '8621', 'A', 'u', 'w', 'h', '7487', '5757', 'r', '5851', 'n', 'N', '8359', 'e', '3553', '8845', 'e', 'V']\nanswer:\n" }, { "from": "gpt", "value": "A, u, w, h, 7487, 5757, r, 5851, n, N, 8359, e, 3553, 8845, e, V\n\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: In 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'.\nProblem:Title: 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.\nSolution:" }, { "from": "gpt", "value": "34125" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. 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.\n\nIt is usually Arsenal that are sending opposition defenders into a spin with their intricate pass and move football, but they were given a taste of their own medicine on Wednesday. Mikel Arteta and Theo Walcott took a break from training in the torrential rain at the club's London Colney headquarters to take part in the dizzy penalty challenge craze that is sweeping the internet -even manager Arsene Wenger and mascot Gunnersaurus get involved. There was a sombre mood at Arsenal after they fired another blank at the Emirates during a goalless draw with Liverpool on Monday night, but the squad had that giddy feeling back despite the miserable weather in Hertfordshire.Mikel Arteta and Theo Walcott took part in the dizzy penalty challengeDespite their giddiness both managed to score their respective spot kicksArsenal mascot Gunnersaurus also took a turn but miss-hot his penaltyManager Arsene Wenger found the whole thing hilarious \n Questions:'This is _ and this is his dizzy penalty,' the Arsenal boss says. (A) Arsenal (B) Mikel Arteta (C) Theo Walcott (D) London Colney (E) Arsene Wenger (F) Gunnersaurus (G) Emirates (H) Liverpool (I) Hertfordshire\n" }, { "from": "gpt", "value": "(F)" } ]
[ { "from": "human", "value": "In this task, you're given the beginning and the middle of a three-part story. Your job is to complete the short story by writing a probable ending. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra information when creating the ending, and use names instead of pronouns (e.g. he / she) wherever possible.\n\n[Q]: Beginning: Shelly's teacher arranged a circle of chairs. Middle: She then sat down in one of the chairs.\n[A]: Unfortunately, she sat right on a boy's lap.\n\n\n[Q]: Beginning: Alex was in his bedroom. Middle: A man broke into Alex's bedroom window.\n[A]: It changed Alex forever.\n\n\n[Q]: Beginning: Jill fell asleep with her hair color in! Middle: Jill called her sister to help her.\n[A]:" }, { "from": "gpt", "value": "Together they were able to get her hair back to dark brown.\n\n\n" } ]
[ { "from": "human", "value": "You are provided with an \"Event\" and it's \"Intent\" related to PersonX. Determine the sentiment value of the given input as either \"Positive\", \"Negative\", and \"Unknown\". \nQ: Event:PersonX has a hard time. Intent: 1) to exercise themselves 2) to be physically healthy 3) to challenge themselves\nA: " }, { "from": "gpt", "value": "Unknown" } ]
[ { "from": "human", "value": "Detailed Instructions: 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.\nProblem:Premise: PersonX gets PersonY's new car\nHypothesis: Because PersonX wanted to make y happy\nUpdate: PersonX took the car away and sold it.\nSolution:" }, { "from": "gpt", "value": "weakener" } ]
[ { "from": "human", "value": "In this task, you are given a short story consisting of exactly 5 sentences where the second sentence is missing. You are given two options and you need to select the one that best connects the first sentence with the rest of the story. Indicate your answer by 'Option 1' if the first option is correct, otherwise 'Option 2'. The incorrect option will change the subsequent storyline, so that at least one of the three subsequent sentences is no longer consistent with the story.\n--------\nQuestion: Sentence 1: A few days ago, I had been walking to the park. \n Sentence 3: I tried to walk away from them but they started threatening me \n Sentence 4: When I left, I spoke to the police about them \n Sentence 5: The police spoke to the men and made them leave \n Option 1: I had a picnic and my friends joined me. \n Option 2: When I arrived, I saw some strange men running quickly towards me.\n\nAnswer: Option 2\n\n\nQuestion: Sentence 1: Cody was home alone with her son when she saw a horrible sight. \n Sentence 3: She didn't know what to do without her husband there \n Sentence 4: She decided to get a bowl to trap the mouse underneath \n Sentence 5: The mouse stayed trapped under the bowl all day until her husband came \n Option 1: In her kitchen there was a mouse! \n Option 2: In her kitchen there was a strange man!.\n\nAnswer: Option 1\n\n\nQuestion: Sentence 1: The surgeon was working on a patient's wisdom teeth. \n Sentence 3: He ended up messing up \n Sentence 4: Since he made the patient sign a waiver, the patient could not sue \n Sentence 5: The patient wrote a bad review online though \n Option 1: He decided to leave them in. \n Option 2: He had to take out 4 of them.\n\nAnswer:" }, { "from": "gpt", "value": "Option 2\n\n\n" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nGiven a story, answer the question about the story. The question is the last sentence in the input. The story has one of the three following scenarios: (1) when the individual's belief matches reality, (2) when the individual's belief does not match reality, (3) 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.\n\nHannah entered the front_yard. Lucas entered the front_yard. The tangerine is in the green_crate. Lucas exited the front_yard. Hannah moved the tangerine to the blue_container. Where will Lucas look for the tangerine?\nOutput:" }, { "from": "gpt", "value": "green_crate" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task you will be given a list of integers. You should round each integer to the nearest tens place. That means you should round the number to the nearest multiple of 10.\n\n[294, 34, -255, -200, -210, -170]\n" }, { "from": "gpt", "value": "[290, 30, -260, -200, -210, -170]" } ]
[ { "from": "human", "value": "instruction:\nIn this task you will be given a list of numbers and you need to subtract every value in the list with the index it is at. The index of an elements shows its numerical order in the list(for example, in the list [7,10,4,5], the index of 7 is 1 and the index of 4 is 3) You should start the index at 1, so the first element in the list will be subtracted by one. For every element in the list you need to find \"element - index\" where the index of the beginning element is 1 and increments by 1 for each element. Put your result list in brackets.\nquestion:\n[2, -9, -2, 7, 5, -4, -19, 12, -9, -8]\nanswer:\n[1, -11, -5, 3, 0, -10, -26, 4, -18, -18]\n\n\nquestion:\n[17, 4, 2, -11, 2, -7, 19, 11]\nanswer:\n[16, 2, -1, -15, -3, -13, 12, 3]\n\n\nquestion:\n[7, -8, 12, -4, -20, 14, 0]\nanswer:\n" }, { "from": "gpt", "value": "[6, -10, 9, -8, -25, 8, -7]\n\n\n" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you are given a sentence from the research paper and your task is to classify the given sentence into the following categories: Background (Why is this problem important? What relevant works have been created before? What is still missing in the previous works? What are the high-level research questions? How might this help other research or researchers?), Purpose (What specific things do the researchers want to do? What specific knowledge do the researchers want to gain? What specific hypothesis do the researchers want to test?), Method (How did the researchers do the work or find what they sought? What are the procedures and steps of the research?), or Finding (What did the researchers find out? Did the proposed methods work? Did the thing behave as the researchers expected?). \n\nEfforts to control future SARS outbreaks depend on the accurate and early identification of SARS-CoV infected patients.\nSolution: background\nWhy? The sentence provides the background information regarding how they could control future SARS outbreaks depending on the accuracy of identification of some infected patients having SARS-CoV.\n\nNew input: management methods , and clinical outcomes.\nSolution:" }, { "from": "gpt", "value": "method" } ]
[ { "from": "human", "value": "In this task you will be given a list of numbers and you should remove all duplicates in the list. If every number is repeated in the list an empty list should be returned. Your list should be numbers inside brackets, just like the given list.\n\n[2, 1, 3, 1, 3, 0, 2, 4, 4]" }, { "from": "gpt", "value": "[0]" } ]
[ { "from": "human", "value": "Part 1. Definition\nGiven a sentence, generate a most unlikely next statement. The next statement should not be logically relevant to the given context\nPart 2. Example\nThe girls continue to speak with one another while the girl knits. They\nAnswer: put the bars around while speaking and play.\nExplanation: This is incorrect as the girls are not playing, they are knitting.\nPart 3. Exercise\nHis green cape flapping behind him, he joins his teammates, who flank him as they charge for goal. Fending off Gryffindor players, they\nAnswer:" }, { "from": "gpt", "value": "race to the surface of the pool." } ]
[ { "from": "human", "value": "Q: 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.\nContext : When the Sioux came into Canada, fleeing pursuing American forces, Crowfoot made peace with Sitting Bull and his tribe. \nQuestion : What medical condition did Crowfoot have?\nA:" }, { "from": "gpt", "value": "medical condition" } ]
[ { "from": "human", "value": "Definition: You are given a paragraph (Passage), a question (Question) and two answer options (Option1 and Option2). Your task is to choose the correct answer to the question based on the passage. Answer of the question cannot be found directly from the passage, it is indirectly indicated in the passage. Do not answer with words other than the two options, and do not answer with option titles(e.g. \"option1\" or \"1\" are not acceptable answers.)\nInput: Passage: I was driving to work when I noticed that my gas tank was low . I like keeping a full tank , so at the next gas station I pulled in and pulled up to the gas hoses . I shut my engine off and got out of my car , making sure I had my wallet in my back pocket . There 's a number pad and a slot on the pump for your credit card or debit to go in . I made sure it was in , then pressed the buttons I needed to to get ten gallons of gas . I had to put my pin number for the card in , and my zip code . Once I saw that , I pumped the ten gallons I had paid for with my debit card . It was expensive , but I always feel more secure when I have a full gas tank , so that 's a good thing . Question: What does the screen say is ok to pump? Option1: Gas Option2: 1 gallon\nOutput:" }, { "from": "gpt", "value": "Gas" } ]
[ { "from": "human", "value": "Instructions: Given a sentence, generate a most unlikely next statement. The next statement should not be logically relevant to the given context\nInput: It rumbles beneath a car. The crack\nOutput:" }, { "from": "gpt", "value": "seems to light his room." } ]
[ { "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: 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.\nSolution is here: Tom had been shopping for fruit to give Jon.\nExplanation: 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.\n\nNow, solve this: Sentence 1: Two men, one wearing a yellow shirt and one wearing a red shirt, being pulled by horses. Sentence 2: There are two male men\nSolution:" }, { "from": "gpt", "value": "Two men sitting in a sleigh are pulled by horses." } ]
[ { "from": "human", "value": "You are supposed to identify the category of a high-school level math question. There are five possible categories (1) algebra (2) arithmetic (3) measurement (4) numbers, and (5) probability. Use the following guidelines: (1) 'algebra' questions will typically contain letter variables and will ask you to find the value of a variable (2) 'arithmetic' questions will ask the sum, difference, multiplication, division, power, square root or value of expressions involving brackets (3) 'measurement' questions are questions that ask to convert a quantity from some unit to some other unit (4) 'numbers' questions will be about bases, remainders, divisors, GCD, LCM etc. (5) 'probability' questions will ask about the probability of the occurrence of something. A question must belong to only one category.\n\nSolve 0 = -4*j - 906 + 894 for j." }, { "from": "gpt", "value": "algebra" } ]
[ { "from": "human", "value": "You are given an original reference as well as a system generated reference. Your task is to judge the naturaleness of the system generated reference. If the utterance could have been produced by a native speaker output 1, else output 0.\n\nExample input: System Reference: x is a reasonably priced fast food restaurant down by river cheap.\nOriginal Reference: x is a cheap fastfood restaurant located near the riverside.\nExample output: 1\nExample explanation: The system reference could have been uttered by a native speaker.\nQ: System Reference: x is a restaurant in the x, riverside to located and x.\nOriginal Reference: x is a restaurant on the riverside close to x. it is near x in x.\nA:" }, { "from": "gpt", "value": "0" } ]
[ { "from": "human", "value": "A piece of text from one of these 5 languages - French, English, Dutch, Somali, Tagalog is given. Generate the language to which the text belongs.\n\nLet me give you an example: Text: Cheval de soins pour les enfants de 3 ans!\nThe answer to this example can be: French\nHere is why: The given text is in French language\n\nOK. solve this:\nText: Jullie hebben meer voor MIJ gedaan dan velen die zichzelf pastors noemen, en helemaal geen pastors zijn.\nAnswer:" }, { "from": "gpt", "value": "Dutch" } ]
[ { "from": "human", "value": "Teacher: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.\nTeacher: Now, understand the problem? Solve this instance: I_TURN_LEFT I_JUMP I_TURN_LEFT I_JUMP I_TURN_LEFT I_JUMP I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT\nStudent:" }, { "from": "gpt", "value": "turn around left twice after jump left thrice" } ]
[ { "from": "human", "value": "In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to determine if the two sentences clearly agree/disagree with each other, or if this can't be determined. Indicate your answer as yes or no respectively.\nExample: Sentence 1: Next to the MGM Grand you will find M and M World. Sentence 2: The candy has many fans who love its attractions.\nExample solution: no\nExample explanation: It is not clear that M and M world is popular.\n\nProblem: Sentence 1: well because it actually is yeah it's better than cash Sentence 2: Because it is better than cash.\n" }, { "from": "gpt", "value": "Solution: yes" } ]
[ { "from": "human", "value": "In this task, you are given an input list A. You need to extract and sort the unique digits used in the list in ascending order. Return -1 if there is no digit in the list.\nExample: ['q', '31', 'a', 'd', '53', '85', 'p', '77']\nExample solution: 1, 3, 5, 7, 8\nExample explanation: Here, the numbers in the list are '31', '53', '85' and '77', and the unique digits used in the list are '1, 3, 5, 7, 8' in ascending order.\n\nProblem: ['r', '199', 'p', '459', '395', '123', 'p', '285']\n" }, { "from": "gpt", "value": "Solution: 1, 2, 3, 4, 5, 8, 9" } ]
[ { "from": "human", "value": "Teacher: Given news headlines, an edited word and funniness labels. The original sentence has word with the given format {word}. Create new headlines by replacing {word} in the original sentence with edit word. Your task is to generate answer \"Yes\" if an edited sentence matches funniness label, otherwise generate answer \"No\". \nTeacher: Now, understand the problem? If you are still confused, see the following example:\nNews Headline: Top Senate Democrat promises fight to {block} Trump high court pick. \n Edit: gift \n Label: Not Funny \nSolution: Yes\nReason: The funniness label is Not Funny because an edited sentence is not making much sense.\n\nNow, solve this instance: News Headline: ' We have plenty of time ' : Congress may delay decision on fate of 700,000 {Dreamers} \n Edit: nightmares \n Label: Not Funny\nStudent:" }, { "from": "gpt", "value": "No" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you are given inputs i and A, where i is an integer and A is a list. You need to list all the elements of A preceding the last i elements. i will always have a value less than the length of A.\nExample: 3, ['a', '34', 'f', '931', '7', '3432', '13245', '762']\nOutput: a, 34, f, 931, 7\nHere, all the elements except the last 3 from the list are 'a', '34', 'f', '931', and '7'.\n\nNew input case for you: 10, ['7579', 'I', '6425', '5409', 'R', '8753', '1545', 'e', 'w', 'x', 'g', 'k', '2205', '5723', '4317', 'i', '9447', '9367', 'p', 'O', 's', '5107', '267', '9831']\nOutput:" }, { "from": "gpt", "value": "7579, I, 6425, 5409, R, 8753, 1545, e, w, x, g, k, 2205, 5723" } ]

Subsets and Splits

No community queries yet

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