Split (1)

train · 8.3M rows

Search is not available for this dataset

conversations listlengths 2 2
[ { "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 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, 3, ['3793', '6737', 'G']\nOutput:" }, { "from": "gpt", "value": "10530" } ]
[ { "from": "human", "value": "In this task, you are given a sentence in the Bulgarian language and corresponding English translation of this sentence. Here, your job is to generate label \"yes\" if translation is right, otherwise generate label \"no\".\n\nBulgarian: 8., English: Delegation to EUROLAT (vote)" }, { "from": "gpt", "value": "no" } ]
[ { "from": "human", "value": "Given the prompt and a response, classify the them to \"yes\" if response is \"yes, and\" type. Otherwise classify it as \"no\". \"Yes, and\" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated (\"Yes\") and then expand on that line of thought or context (\"and...\"). 1 In short, a \"Yes, and\" is a dialogue exchange in which a speaker responds by adding new information on top of the information/setting that was constructed by another speaker. Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange, although it could be the case if it agrees with the description above. There are many ways in which a response could implicitly/explicitly agree to the prompt without specifically saying 'yes, and...'. \nOne example: Prompt: I'm glad you came into my office today, young man. Look around you. Everything that's in here, I purchased. \n Response: Wow! You own everything in this office?\nSolution is here: yes\nExplanation: This is correct answer because response is in support with the prompt and extends the context from prompt.\n\nNow, solve this: Prompt: Alright, Pip, that's enough. Go have a seat. \n Response: That is true, but I also have a long beard and am frequently wet.\nSolution:" }, { "from": "gpt", "value": "no" } ]
[ { "from": "human", "value": "We would like you to classify each of the following sets of argument pairs (discussing Gun Control) into either SIMILAR or NOT SIMILAR. A pair of arguments is considered SIMILAR if the arguments are about the same FACET (making the same argument), and is considered NOT SIMILAR if they do not have the same FACET. A FACET is a low level issue that often reoccurs in many arguments in support of the author's stance or in attacking the other author's position.\nQ: Sent1: The reality is that in developed nations with stricter gun laws than the US there are less outlaws owning and using guns.\n Sent2: Some studies used against gun have been ones showing that over 50% of homicides in the US are committed with guns, while in countries with gun bans or very strict gun control have a lower amount of gun homicides.\nA: " }, { "from": "gpt", "value": "Not similar" } ]
[ { "from": "human", "value": "TASK DEFINITION: You need to create a question containing a blank (_), based on the given context word. Your question must contain two persons --PersonX and PersonY. The expected answer to your question must be PersonX. PersonX and PersonY should not be equally likely to fill the blank. 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 question. 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 Person X and Person Y have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY.\nPROBLEM: Context Word: jump.\n\nSOLUTION: PersonX put their foot in their mouth and embarrassed themselves, unlike PersonY, because _ always jumped to conclusions.\n\nPROBLEM: Context Word: grad school.\n\nSOLUTION: Grad school was a chore for PersonX but fun for PersonY, since _ hated studying and taking tests.\n\nPROBLEM: Context Word: upsell.\n\nSOLUTION:" }, { "from": "gpt", "value": "In an effort to increase commissions, PersonX pushed PersonY hard to buy the addon products that _ was trying to upsell.\n\n" } ]
[ { "from": "human", "value": "Q: 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 to not connect with the rest of the story. Ensure that the generated sentence is contextually relevant to the story.\nTitle: The library. Sentence 1: They had a fun event at the library the other night. Sentence 2: They had a reptile place come. Sentence 3: They did a show and touch with the animals. Sentence 4: They had a lot of exotic animals there.\nA:" }, { "from": "gpt", "value": "He was dismayed to have fried his microprocessor." } ]
[ { "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.\nProblem:Sentence1: Sounds great- thanks for your help! Sentence2: Have a great visit! Sentence3: You're all set. Your Reference number is : T9VLKXV5 . Sentence4: No thanks, but can I just get some information about Cityroomz? Sentence5: Hello! I'm needing a place to stay in the center of town. Parking is not important to me. What do you have? Sentence6: I have a moderately priced hotel called Cityroomz available. Can I help you book your stay? Sentence7: I would like to book 5 nights on sunday for 5. Sentence8: Cityroomz is a moderatly priced 0-star hotel in the centre. They offer internet and parking and are located on station road. Question: Who has spoken the sentence 6? (A) User (B) System\nSolution:" }, { "from": "gpt", "value": "Answer: (A) User" } ]
[ { "from": "human", "value": "Instructions: 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.\nInput: Title: New neighbor's. Sentence 1: He was excited. Sentence 2: It looked like he got new neighbors. Sentence 3: Fred looked outside. Sentence 4: He went to introduce himself. Sentence 5: He made some friends.\nOutput:" }, { "from": "gpt", "value": "31" } ]
[ { "from": "human", "value": "Instructions: In this task, you will be shown a passage. You need to write a fill-in-the-gap question based on your understanding of the events that might be inferred from the passage. Your question should be answerable based on the passage and only have one correct answer. Show the gap in your question with a _ .\nInput: (CNN) -- The United Arab Emirates will try 94 people on charges of seeking to seize power, the UAE's state news agency WAM reported Sunday. Most of them were detained in September and are only now being charged, CNN learned. \"They launched, established and ran an organisation seeking to oppose the basic principles of the UAE system of governance and to seize power,\" Attorney General Salem Saeed Kubaish said in a statement published by WAM. Those arrested were sent to to the Federal Supreme Court. The group is apparently part of an organization that Kubaish said was established to teach the \"virtues of Islam.\" It intended to take over the government and \"oppose the basic principles of the system,\" he said.NEW: Most of the suspects were detained in September and are only now being chargedGovernment accuses them of meeting in secret, using social media to stir unrestSome arrested are allegedly part of al-Islah; government links them to Muslim BrotherhoodSome group members say they're activists, but distance themselves from other groups\nOutput:" }, { "from": "gpt", "value": "The detainees are also accused of receiving financial support and expertise from the _ \"to serve their undeclared goal of seizing power.\"" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nGiven a sentence in Somali language, translate the sentence to English language keeping the meaning of the original sentence intact\n\nSomali sentence: Lionel Messi waa ciyaaryahanka ugu weyn kubadda cagta abid\nSolution: Lionel Messi is the greatest football player of all time\nWhy? The output exactly translates the Somali sentence to it's English equivalent. Even though the phrase 'greatest player ever' is translated to 'greatest player of all time', the meaning remains the same.\n\nNew input: Somali sentence: Boqortooyadii ka dambeysay Suldanadii Cadal\nSolution:" }, { "from": "gpt", "value": "A successor kingdom to the Sultanate of Adal" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task you will be given two dialogues. You need to determine if both dialogues have the same underlying emotion. The possible emotions are happy, sad, angry, or other. If they do output 'yes', if not output 'no'.\nExample: Dialogue 1: 'when did i called u ugly pony when did you ever call fuck u ur rlly a mad person asshole rnda bc'. Dialogue 2: 'go to dhapar math do sl maths a lot of places don't like maths studies it's amazing'.\nOutput: no\nThe first dialogue is an angry dialogue and the second dialogue is a happy dialogue. Therefore, they are not the same emotion so the output is 'no'. So this is a good example.\n\nNew input case for you: Dialogue 1: 'you are soo beautiful i knowand thanks d and look sooo nice'. Dialogue 2: 'cool i agree cool info plz send me pictures'.\nOutput:" }, { "from": "gpt", "value": "no" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nYou will be given a person's personality, and a history of a conversation this person has had. You will be given four candidate sentences to complete the conversation, based on the context. Choose one and answer with the text.\n\nPersonality: My father used to be a mechanic.\nI am a musician.\nI've been working the same job for two years.\nI like to play video games.\nChat history: -\nCandidates 1) Are you listening music? 2) Hi! I enjoy playing piano for a living. What do you do? 3) Yes. It is so expensive. Are you good at math and science? I am excellent at it. 4) Hi how are you doing today.\nOutput:" }, { "from": "gpt", "value": "Hi! I enjoy playing piano for a living. What do you do?" } ]
[ { "from": "human", "value": "Teacher: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.\nTeacher: Now, understand the problem? Solve this instance: Sentence: 'a bird stands on top of the statue'. Reverse all words of length '3' in the given sentence.\nStudent:" }, { "from": "gpt", "value": "a bird stands on pot of eht statue" } ]
[ { "from": "human", "value": "Detailed Instructions: 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).\nQ: yttrium\nA:" }, { "from": "gpt", "value": "silvery-metallic lustre" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nGiven a 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.\n\nI_TURN_LEFT I_JUMP\nSolution: jump left\nWhy? If the agent turned to the left and jumped, then the agent jumped to the left.\n\nNew input: I_TURN_LEFT I_TURN_RIGHT I_TURN_RIGHT I_RUN\nSolution:" }, { "from": "gpt", "value": "run opposite right after turn left" } ]
[ { "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\nred bean\n" }, { "from": "gpt", "value": "skin" } ]
[ { "from": "human", "value": "The task is to generate the correct answer for a given math problem.\nExample: a multiple choice test consists of 4 questions, and each question has 5 answer choices. in how many r ways can the test be completed if every question is unanswered ?\nExample solution: 625\nExample explanation: Total r of 5 * 5 * 5 * 5 = 5 ^ 4 = 625 ways to answer all of them. Therefore, the answer is 625.\n\nProblem: Problem: find ( 7 x + 2 y ) / ( x - 2 y ) if x / 2 y = 3 / 2 ?\n" }, { "from": "gpt", "value": "Solution: 23" } ]
[ { "from": "human", "value": "Detailed Instructions: In 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.\nProblem:i feel strange and weird about this entire struggle am i the only one who deals with this kind of conflict\nSolution:" }, { "from": "gpt", "value": "fear" } ]
[ { "from": "human", "value": "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.\n\nExample Input: Category: AMERICAN INDIANS \nClue: This famed Sauk Indian had both a war and a pro sports team named for him\nExample Output: black hawk\n\nExample Input: Category: MUSIC LEGENDS \nClue: His 2003 People magazine obituary was headlined \"Fade to Black\"\nExample Output: johnny cash\n\nExample Input: Category: GEOGRAPHY \nClue: 2 of the 4 U.S. states that border Mexico\nExample Output:" }, { "from": "gpt", "value": "texas, new mexico, arizona, california\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: The provided file includes inquiries about restaurants in Italian, and we ask you to translate those to English language. Please bear in mind the following guidelines while doing the translation: 1) We are looking for the most naturally written and formal form of each sentence in your language. We are NOT looking for colloquial forms of the sentence. We are looking for formal form which is how you would type your queries in a text-based virtual assistant. 2) The words between quotation marks SHOULD NOT be translated. We expect you to keep those values intact and include the quotation marks around them as well. 3) The fully capitalized words like DATE_0, or DURATION_0 SHOULD NOT be translated. Please keep them as they are in the translations. 4) Please do not localize measurement units like miles to kilometers during your translation. miles should be translated to its equivalent in your language. 6) Note the input is all lowercased except for fully capitalized special placeholders (e.g. NUMBER, DATE, TIME). Please do the same in your translations.\nQ: mostrami tutti i ristoranti \" chinese \" con valutazioni di 3 stelle entro un raggio di 1 miglia.\nA:" }, { "from": "gpt", "value": "show me all \" chinese \" restaurants with 3 star ratings within 1 miles ." } ]
[ { "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\nQ: Context Word: guardian.\nA: " }, { "from": "gpt", "value": "The man finally decided to become a guardian for the child at the orphanage because the _ was isolating." } ]
[ { "from": "human", "value": "TASK DEFINITION: In mathematics, the absolute value of a number is the non-negative value of that number, without regarding its sign. For example, the absolute value of -2 is 2, and the absolute value of 5 is 5. In this task you will be given a list of numbers and you need to return the element with highest absolute value. If a negative and positive element have the same absolute value you should return the positive element. The absolute value for negative numbers can be found by multiplying them by -1. After finding the element with the maximum absolute value you should return the value of that element before you applied the absolute value.\nPROBLEM: [58.947 43.175 70.564]\n\nSOLUTION: 70.564\n\nPROBLEM: [-11.569 -5.703 -91.937]\n\nSOLUTION: -91.937\n\nPROBLEM: [ 74.36 -40.341 62.409 -4.246 14.067 9.463 -2.399 -86.371]\n\nSOLUTION:" }, { "from": "gpt", "value": "-86.371\n\n" } ]
[ { "from": "human", "value": "TASK DEFINITION: You are provided with an \"Event\", \"Intent\" and \"XEmotion\" (PersonX's reactions for the given \"Event\"). Indicate PersonY's reaction (person feels) at the end of this event. Provide one reaction for PersonY. If there's nothing that can be implied, respond as None\nPROBLEM: Event:PersonX takes PersonY along. Intent:. XEmotion: 1) neutral\n\nSOLUTION: encouraged\n\nPROBLEM: Event:PersonX leaves the ___ better. Intent: 1) persony to be happy 2) to see how it looks on someone. XEmotion: 1) happy 2) glad to know it fits\n\nSOLUTION: okay\n\nPROBLEM: Event:PersonX stuffs the ballot box. Intent: 1) to eat the banana 2) to be healthy. XEmotion: 1) satisfied to feed their hunger 2) healthy\n\nSOLUTION:" }, { "from": "gpt", "value": "a great sense of loss\n\n" } ]
[ { "from": "human", "value": "In this task, you are given a context paragraph, a question based on that and corresponding answer of a question. Your task is to generate supporting fact/knowledge from context paragraph which helps in answering a given question.\n\nThe 3rd IAAF World Athletics Final was held at the Stade Louis II, in Monte Carlo, Monaco on September 9, and September 10, 2005. Question: The 3rd IAAF World Athletics Final was held at a stadium that serves primarily as the home stadium of which teams ? Answer: AS Monaco and the Monaco national football team" }, { "from": "gpt", "value": "The 3rd IAAF World Athletics Final was held at the Stade Louis II, in Monte Carlo, Monaco on September 9, and September 10, 2005." } ]
[ { "from": "human", "value": "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.\nQ: concept: German Language question: what countries speak german as a first language?\nA: " }, { "from": "gpt", "value": "['Canada', 'German Democratic Republic', 'Luxembourg', 'Switzerland', 'Liechtenstein', 'Germany', 'West Germany', 'Belgium', 'Vatican City', 'Second Polish Republic']" } ]
[ { "from": "human", "value": "Q: In this task, you need to answer the given multiple-choice question on the physics. Classify your answers into 'a', 'b', 'c', 'd', and 'e'.\nProblem: three pipes , a , b , & c are attached to a tank . a & b can fill it in 20 & 30 minutes respectively while c can empty it in 15 minutes . if a , b & c are kept open successively for 1 minute each , how soon will the tank be filled ? \nOptions: a ) 2 hours , b ) 4 hours , c ) 3 hours , d ) 5 hours , e ) 6 hours\nA:" }, { "from": "gpt", "value": "c" } ]
[ { "from": "human", "value": "In this task, you're given a context passage, an answer, and a question. Your task is to classify whether the question for this answer is correct or not, based on the given context with commonsense reasoning about social situations. If its correct ,return \"True\" else \"False\".\n\nQ: Context: Jesse thanked Bailey's boss for Bailey's support even though Bailey hardly did any of the work. \n Answer: grateful \n Question: How would Bailey feel as a result?\n\nA: True\n**\nQ: Context: Austin bucked down and decided to spend all afternoon working. \n Answer: take a break \n Question: What will Austin want to do next?\n\nA: True\n\nQ: Context: Jan left Riley's keys for them because she could not drive. \n Answer: very responsible \n Question: How would you describe Jan?\n\nA:" }, { "from": "gpt", "value": "True\n**\n" } ]
[ { "from": "human", "value": "TASK 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.\nPROBLEM: Title: Pet Monkey. Sentence 1: Tom always wanted a pet monkey. Sentence 2: He looked online and found some options. Sentence 3: He saved up for a while until he could buy one. Sentence 4: Tom finally was able to get the pet. Choices: a. He loved it for several years. b. Rescue teams finally found him relatively safe.\n\nSOLUTION: a\n\nPROBLEM: Title: Anger. Sentence 1: Ivan was playing at a local tennis tournament. Sentence 2: And it was his turn to serve. Sentence 3: But he double faulted and became very angry. Sentence 4: And he threw is racket at the ground. Choices: a. Laurie had to hire a professional painter to finish the job. b. But Ivan felt regretful after being penalized.\n\nSOLUTION: b\n\nPROBLEM: Title: Too Much. Sentence 1: My daughter likes to work out with me when I do exercises. Sentence 2: After I do an exercise she will try to mimic it. Sentence 3: When I do military presses with dumbbells she also tries. Sentence 4: But she cannot even lift them off the floor. Choices: a. The police suggested he get a security system. b. This always makes me feel very strong for some reason.\n\nSOLUTION:" }, { "from": "gpt", "value": "b\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input 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. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\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\nProblem:Context Word: yard sale. \nQuestion: While shopping at the yard sale, the woman passed on the dishes, but bought the spoons, because she already had many of the _ . \nAnswer: dishes.\nSolution:" }, { "from": "gpt", "value": "While shopping at the yard sale, the woman passed on the dishes, but bought the spoons, because she needed more of the _ ." } ]
[ { "from": "human", "value": "Detailed Instructions: The provided file includes inquiries about restaurants, and we ask you to translate those to the German language. Please bear in mind the following guidlines while doing the translation: 1) We are looking for the most naturally written and formal form of each sentence in your language. We are NOT looking for colloquial forms of the sentence. We are looking for formal form which is how you would type your queries in a text-based virtual assistant. 2) The words between quotation marks are named entities and SHOULD NOT be translated. We expect you to keep those values intact and include the quotation marks around them as well. 3) The fully capitalized words like DATE_0, or DURATION_0 SHOULD NOT be translated. Please keep them as they are in the translations. 4) Please do not localize measurement units like miles to kilometers during your translation. miles should be translated to its equivalent in your language. 5) Note the input is all lowercased except for special placeholders. Please do the same in your translations.\nProblem:is there a restaurant in zipcode \" 19101 \" ?\nSolution:" }, { "from": "gpt", "value": "gibt es ein restaurant innerhalb der plz \" 19101 \" ?" } ]
[ { "from": "human", "value": "Instructions: Classify the given a piece of financial news into three classes: positive, negative, and neutral. Output must be 'positive', 'negative', or 'neutral'.\nInput: Under this agreement Biohit becomes a focus supplier of pipettors and disposable pipettor tips to VWR customers throughout Europe .\nOutput:" }, { "from": "gpt", "value": "positive" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a sentence that is either in the Yoruba language or the English language. Your task is to identify the language of the input sentence. Input sentences should be in Yoruba or English language and also it cannot have two languages at a time.\nProblem:Open-heart surgery in Nigeria -- big trouble.\nSolution:" }, { "from": "gpt", "value": "English" } ]
[ { "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 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.\n\nContext: Sasha worked for weeks. They saved a lot of money during that time. \n Question: What does Sasha need to do before this? \n Options: (A) make time (B) work overtime (C) not manage time\nOutput:" }, { "from": "gpt", "value": "C" } ]
[ { "from": "human", "value": "In this task, you are given an input list A. You need to find all the elements of the list that are numbers and calculate their sum.\n\nExample input: ['238', 'h', '92', 'U', '2799']\nExample output: 3129\nExample explanation: Here, the numbers in the input list are '238', '92' and '2799', hence their sum (238+92+2799) is 3129.\nQ: ['Q', 'o', '9717', 'W', '5419', 'C', 'v', 'S', '1601', '9923', '6063', 'D', '5191', '775']\nA:" }, { "from": "gpt", "value": "38689" } ]
[ { "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: insult and non-insult. Insult is any lanugage or act that is disrespectful or scornfully abusive.\n\nQ: Comment: you're a piece of shit\n\nA: Insult\n**\nQ: Comment: \"I made sure I had my bear bell on and bear spray with me...\" Yeah, right. Next time have a gun strapped to your back, idiot!\n\nA: Insult\n\nQ: Comment: The real issue is not how much area they capture, but how many terrorists they exterminate. More, the better.\n\nA:" }, { "from": "gpt", "value": "Non-insult\n**\n" } ]
[ { "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\nLet me give you an example: 5 + 3\nThe answer to this example can be: 2\nHere is why: Here, '+' represents subtraction operation. So, the answer is 2 (5-3=2).\n\nOK. solve this:\n8592 - 2506 - 6371\nAnswer:" }, { "from": "gpt", "value": "17469" } ]
[ { "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? If you are still confused, see the following example:\nSentence 1: Jon saw his friend Tom coming out of the grocery store with a bag of fruit. Sentence 2: Tom had not been in the store.\nSolution: Tom had been shopping for fruit to give Jon.\nReason: 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 instance: Sentence 1: A woman with green hair is swinging at a pinata. Sentence 2: The woman with red hair is hitting the pinata.\nStudent:" }, { "from": "gpt", "value": "The woman swings the stick wildly." } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you need to provide the parts-of-speech tag of a word present in a sentence specified within curly braces ( '{{ ... }}' ). The parts-of-speech tags are 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.\nQ: Sentence: In the play Holofernes is ridiculing Don Adriana \" the traveler from Spain \" and says of him : \" He {{ is }} too picked , too spruce , too affected , Too odd , as it were , too PEREGRINate , as I may call it . \" \nWord: is\nA:" }, { "from": "gpt", "value": "VBZ" } ]
[ { "from": "human", "value": "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.\n\nEx Input:\nconcept: North Korea question: what government type is north korea?\n\nEx Output:\n['Juche']\n\n\nEx Input:\nconcept: Martin Luther King Jr question: where did dr martin luther king get his doctorate?\n\nEx Output:\n['Boston University']\n\n\nEx Input:\nconcept: Alani Vasquez question: where does lala anthony live?\n\nEx Output:\n" }, { "from": "gpt", "value": "['Brooklyn']\n\n\n" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nGiven an Amazon customer review, write a title for the review. The preferred titles are under fifteen words.\n\nthe little rubber things come off if you dont take care of it. but its a great price and it works with any touch screen for phones and ipads. i love it.\nOutput:" }, { "from": "gpt", "value": "for the price awesome" } ]
[ { "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 coarse labels that represent a category of words with similar grammatical properties. The list of part-of-speech tags i.e. tagset of this corpus is 'ADJ': Adjectives are words that typically modify nouns and specify their properties or attributes, 'ADP': Adposition is a cover term for prepositions and postpositions, 'ADV': Adverbs are words that typically modify verbs for such categories as time, place, direction or manner, 'AUX': An auxiliary is a function word that accompanies the lexical verb of a verb phrase and expresses grammatical distinctions not carried by the lexical verb, such as person, number, tense, mood, aspect, voice or evidentiality, 'CCONJ': A coordinating conjunction is a word that links words or larger constituents without syntactically subordinating one to the other and expresses a semantic relationship between them, 'DET': Determiners are words that modify nouns or noun phrases and express the reference of the noun phrase in context, 'INTJ': An interjection is a word that is used most often as an exclamation or part of an exclamation, 'NOUN': Nouns are a part of speech typically denoting a person, place, thing, animal or idea, 'NUM': A numeral is a word, functioning most typically as a determiner, adjective or pronoun, that expresses a number and a relation to the number, such as quantity, sequence, frequency or fraction, 'PART': Particles are function words that must be associated with another word or phrase to impart meaning and that do not satisfy definitions of other universal parts of speech, 'PRON': Pronouns are words that substitute for nouns or noun phrases, whose meaning is recoverable from the linguistic or extralinguistic context, 'PROPN': A proper noun is a noun (or nominal content word) that is the name (or part of the name) of a specific individual, place, or object, 'PUNCT': Punctuation marks are non-alphabetical characters and character groups used in many languages to delimit linguistic units in printed text, 'SCONJ': A subordinating conjunction is a conjunction that links constructions by making one of them a constituent of the other. The subordinating conjunction typically marks the incorporated constituent which has the status of a (subordinate) clause, 'SYM': A symbol is a word-like entity that differs from ordinary words by form, function or both, 'VERB': A verb is a member of the syntactic class of words that typically signal events and actions, can constitute a minimal predicate in a clause, and govern the number and types of other constituents which may occur in the clause, 'X': The tag X is used for words that for some reason cannot be assigned a real part-of-speech category.\n\nExample input: Sentence: An editorial in the church - owned Deseret Morning News in Salt Lake City earlier this year acknowledged that \" the state 's history , a {{ conservative }} belief in free choice , and an unwillingness to stir up a hornet 's nest in the national media have likely all contributed to the kid - glove approach lawmakers and law - enforcement officers have taken when dealing with polygamous communities . \" \nWord: conservative\nExample output: ADJ\nExample explanation: \"conservative\" is an Adjective (ADJ) since it adds to the description of the Noun (NOUN) \"belief\".\nQ: Sentence: A Sri Lanka - born Tamil with a Norwegian passport was arrested by Thai authorities in {{ 2000 }} for his links with the LTTE . \nWord: 2000\nA:" }, { "from": "gpt", "value": "NUM" } ]
[ { "from": "human", "value": "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\nExample input: [5, 8, 9, 3, 7]\nExample output: [22, 2.0, 38, 14, 30]\nExample explanation: The odd numbers, 5, 9, 3, and 7 were multiplied by 4 then added 2. The even number eight was divided by 4.\nQ: [-68, 22]\nA:" }, { "from": "gpt", "value": "[-17.0, 5.5]" } ]
[ { "from": "human", "value": "Instructions: 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.\nInput: I_TURN_RIGHT I_LOOK I_TURN_LEFT I_JUMP I_TURN_LEFT I_JUMP I_TURN_LEFT I_JUMP I_TURN_LEFT I_JUMP\nOutput:" }, { "from": "gpt", "value": "jump around left after look right" } ]
[ { "from": "human", "value": "The task is to generate text based off 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 intent behind doing the event, i.e. why did the person do that action.\n\nPersonX scratches PersonY's head\nto relieve an itch\n\nPersonX takes another drink\nto quench his thirst.\n\nPersonX promotes PersonX's interests\n" }, { "from": "gpt", "value": "to achieve an accomplishment\n\n" } ]
[ { "from": "human", "value": "Q: 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.\n7/8 cup watermelon liquefied, 32 3/4 feet kirsch, ice, cherries for garnish\nA:" }, { "from": "gpt", "value": "watermelon liquefied, feet kirsch, cherries" } ]
[ { "from": "human", "value": "Instructions: In this task, you're given four sentences of a story written in natural language. The given story is not complete and your job is to complete the story by selecting one of the sentence choices from (A) and (B), such that the story sounds fully coherent.\nInput: Sentence1: Brandon was given a 10 page research paper to write for class. Sentence2: He begun working on the paper on his 2003 Dell laptop. Sentence3: Brandon stayed up until 1 in the morning to try and finish his paper. Sentence4: Suddenly, his computer crashed and died. \n (A) When he finished his paper he went to bed. (B) Luckily he had been saving everything on an external disk.\nOutput:" }, { "from": "gpt", "value": "B" } ]
[ { "from": "human", "value": "In this task, you are given an input list A. You need to find all the elements of the list that are numbers and calculate their sum.\n\n['9821', 'w', '5147', '3201', '1309', '7223', 'h', 'B']" }, { "from": "gpt", "value": "26701" } ]
[ { "from": "human", "value": "Definition: You are given an original reference as well as a system reference. Your task is to judge the quality of the system reference. If the utterance is grammatically correct and fluent output 1, else output 0.\nInput: System Reference: may i help you further?\nOriginal Reference: could you please add more info.\nOutput:" }, { "from": "gpt", "value": "1" } ]
[ { "from": "human", "value": "In this task, you will use your knowledge about language (and common sense) to determine what element the marked number refers to. The numbers are marked with two underlines around them, like: _ number _. There are several possible answers, you'll need to choose the proper one. Carefully read the given text, pay special attention to the marked number, think about what (unwritten) information the marked number holds inside, choose the most adequate word(s) from the optional answers. If none of them seems right to you, there's also an option for other. If your answer is \"REFERENCE\", also write the reference entity, otherwise write the implicit option name. Options to choose from are:\nREFERENCE: Some object which is being mentioned in the text before or after the target number. The reference answer has a higher priority than any other. If both Reference and another answer are possible, prioritize the Reference.\nYEAR: Describing a calendric year\nAGE: Describing someone's age\nCURRENCY: Reference to some monetary value e.g dollar, euro etc.\nPEOPLE: Describing a single/plural persons\nTIME: Describing a time of the day. Usually you can add the word o'clock after those numbers.\nOTHER: Some other option, which isn't listed here.\nExample: Jess Mastriani: No, I don't want another crooler, thank you very much.\n FBI Agent Nicole Scott: But it's good for you. It's got... honeyglaze. Please die for this crooler, Jess.\n Jess Mastriani: I've had _ two _ already. Who eats three croolers in a night? \nFBI Agent Nicole Scott: Take a look. [Nicole takes a huge bite] Mmmmm, Mmmmm, Mmmmm!\nExample solution: REFERENCE crooler\nExample explanation: In this example, the number two refers to something that appears in this text. In this example, it refers to the word: crooler.\n\nProblem: Hester Farrell: How much time do you have ?\nAmos Lasher: Time enough to hit _ one _ more outta the park .\n" }, { "from": "gpt", "value": "Solution: OTHER" } ]
[ { "from": "human", "value": "Teacher: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\nTeacher: Now, understand the problem? Solve this instance: The website handles Do Not Track headers in a different way not covered above.\nStudent:" }, { "from": "gpt", "value": "Not specified" } ]
[ { "from": "human", "value": "In this task, you're given a context passage, a question, and three answer options. Your task is to return an incorrect answer option to the question from the choices given. For all questions, only one of the three answer options is correct. Pick one of the two incorrect answer options as the output.\n\nContext: Quinn spent a lot of time with the Kai family with which they were staying in America. \n Question: What will Quinn want to do next? \n Options: (A) clean up after the Kai family (B) learn from Quinn (C) give a gift to the Kai family\nA\n\nContext: Alex walked into a church and started shooting at people, claiming to be administering the lord's wrath. \n Question: What will Others want to do next? \n Options: (A) run from the police (B) evade the police (C) run and hid\nA\n\nContext: Alex was going to visit his cousins in another state. Alex drove all the way from Florida. \n Question: What will Alex want to do next? \n Options: (A) take a tour (B) get gas (C) take a shower\n" }, { "from": "gpt", "value": "C\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element. 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.\nProblem:6, 12, ['4739', 'f', 'v', '2729', 'i', 'c', 'B', '3095', 't', 'k', '5269', '8355', 'r', 'l', '8023', '4787', '6849', '2825', '3097', 'W', '5855']\nSolution:" }, { "from": "gpt", "value": "c, B, 3095, t, k, 5269, 8355" } ]
[ { "from": "human", "value": "Detailed Instructions: Classify the given hotel review based on the sentiment it expresses into two classes: negative and positive.\nProblem:We stayed at the Palmer House Hilton in early December, we stay there that weekend every December and we think it is the best location in the city for us. We like State Street better than Michigan Avenue and the Palmer House is right there. We stayed in the Towers, in a room with two double beds and 2 baths. The room was not huge, but very comfortable. The towers area was recently refurbished and it shows, the lobby is beautiful with plasma screen TVs on the walls, comfortable chairs and tables and a seperate room for the food/drinks. There is a continental breakfast in the morning, appetizers during cocktail hour and cookies are laid out until the room closes. There is a fridge stocked with soft drinks, water and juice that are yours for the taking. We were very pleased with the upgraded Towers, everyone should check it out! \n\nSolution:" }, { "from": "gpt", "value": "positive" } ]
[ { "from": "human", "value": "Teacher: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.\nTeacher: Now, understand the problem? Solve this instance: Premise: PersonX loves riding PersonX's bike\nHypothesis: PersonX then get ready to have fun\nUpdate: PersonX fell off the bike\nStudent:" }, { "from": "gpt", "value": "weakener" } ]
[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nRead 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.\nExample: What is the scientific name of the tortoise ?\nOutput: Good\nThe output for the query is Good because the query has no grammatical, punctuation or spelling errors.\n\nNew input case for you: What will happens when you get tetanus ?\nOutput:" }, { "from": "gpt", "value": "Bad" } ]
[ { "from": "human", "value": "Q: In this task, you're given a context, a sentence, and a character. The sentence describes an action or job of the given character. Also, the context provides more information about the sentence or the character. Your task is to return one of the emotions which are expressed by the Character in the given sentence. For that you can use the Context; however, Context is not provided in all the inputs. Also, in some inputs, there can be zero emotion; for that return 'None'.\nContext: In 1982, my coworkers Tommy and Barbara dated. They ended up in a relationship. \n Sentence: One day they had a fight in the office. \n Character: I (myself)\nA:" }, { "from": "gpt", "value": "alarmed" } ]
[ { "from": "human", "value": "Detailed Instructions: Given a sentence, generate what should be the most likely next statement. The next statement should be reasonable and logically correct.\nQ: Someone beams with newfound optimism. It\nA:" }, { "from": "gpt", "value": ", she sits up again and stretches her hands up." } ]
[ { "from": "human", "value": "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 (\", \").\n\nParagraph- Sent 1: Static electricity is like a teeter-totter.\nSent 2: What happens if a teeter-totter is balanced?\nSent 3: Correct!\nSent 4: It does not move.\nSent 5: What about when its not balanced?\nSent 6: Yes, it will now begin to move.\nSent 7: Charges move when they are not balanced.\nSent 8: Charges can build up by friction.\nSent 9: Maybe you rub your feet on a wool mat or carpet.\nSent 10: Rubber soled shoes readily gain charges.\nSent 11: The wool carpet easily gives up charges.\nSent 12: The two items become unbalanced.\nSent 13: One item has a positive charge.\nSent 14: The other has a negative charge.\nSent 15: The difference in charge is called static electricity.\nSent 16: Just like the teeter-totter, something is going to move.\nSent 17: Positive charges build up on the mat.\nSent 18: Negative charges build up on you. \nQuestion: Does a teeter-totter move if it is balanced?." }, { "from": "gpt", "value": "2, 4." } ]
[ { "from": "human", "value": "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.\n\nExample input: Which writer rode Devon Loch in the 1956 Grand National?\nExample output: dick francis\nExample explanation: The answer is precise and accurately answers the question based on a fact. This is a good example\nQ: Ashtanga Vinyasa, Bikram, and Hatha Vidya are styles of what?\nA:" }, { "from": "gpt", "value": "yoga" } ]
[ { "from": "human", "value": "In this task, you're given a context, a sentence, and a character. The sentence describes an action or job of the given character. Also, the context provides more information about the sentence or the character. Your task is to write the character's motivation by doing a specific job, which is given in the sentence. You can use context to find the motivation; however, all the inputs do not provide context. Also, in some inputs, there can be zero motivation; output, 'None' in this case.\n\n[EX Q]: Context: None \n Sentence: Tim is part of the school soccer team. \n Character: Tim\n[EX A]: None\n\n[EX Q]: Context: None \n Sentence: May was a teacher at a high school. \n Character: May\n[EX A]: need money\n\n[EX Q]: Context: Bill's older brother told him he'd never get a date. He spent too much time playing video games. One day he was at the video game store. \n Sentence: A pretty girl came up beside him, asking his advice on a game. \n Character: Girl\n[EX A]:" }, { "from": "gpt", "value": "some tips on gaming\n\n" } ]
[ { "from": "human", "value": "Given 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: 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.\nExample: Isabella entered the hall. Olivia entered the hall. Phone rang. The apple is in the blue_treasure_chest. Olivia exited the hall. Isabella moved the apple to the green_basket. Where does Isabella think that Olivia searches for the apple?\nExample solution: blue_treasure_chest\nExample explanation: Since Olivia was no longer in the hall, she last remembers the apple being in the blue_treasure_chest even though Isabella moved it to the green_basket. Since Isabella was in the hall the entire time, she knows where Olivia will look for it.\n\nProblem: Oliver entered the dining_room. William entered the dining_room. The grapefruit is in the blue_bathtub. William exited the dining_room. Oliver moved the grapefruit to the red_crate. Oliver exited the dining_room. William entered the dining_room. Where is the grapefruit really?\n" }, { "from": "gpt", "value": "Solution: red_crate" } ]
[ { "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 user profile for an unspecified purpose. Collection happens when you explicitly provide information by some means outside of our label scheme.\nA:" }, { "from": "gpt", "value": "User profile" } ]
[ { "from": "human", "value": "Given a sentence, generate a most likely context or previous statement. The previous statement should be relevant to the given statement.\n\nWhen the video is over the closing credits and graphics are shown on a screen followed by a close up of a heart being rolled away." }, { "from": "gpt", "value": "When the ice cream is done he tastes it and describes how good the flavor is." } ]
[ { "from": "human", "value": "Teacher:Given a scientific question, generate a correct answer to it.\nTeacher: Now, understand the problem? Solve this instance: Algae are much simpler than protozoa. they are aquatic and contain this?\nStudent:" }, { "from": "gpt", "value": "chlorophyll" } ]
[ { "from": "human", "value": "Instructions: Given a sentence in Somali language, translate the sentence to English language keeping the meaning of the original sentence intact\nInput: Somali sentence: 038-027 Maanaan u abuurin Samada iyo Dhulka iyo waxa u dhaxeeya dana laan (Ciyaar).\nOutput:" }, { "from": "gpt", "value": "We did not create the heaven and the earth and everything between them in vain." } ]
[ { "from": "human", "value": "You are given a math word problem and you are supposed to apply a single mathematical operator like addition, subtraction, multiplication, or division on the numbers embedded in the text to answer the following question and then only report the final numerical answer.\n\nInput: Consider Input: there were 44 laptops in the shop and mike divided them equally into 5 rows . how many laptops are there in each row ?\n\nOutput: 8.8\n\n\nInput: Consider Input: mrs. hilt is baking bread . she needs 5 cups of flour to bake 2 loaves of bread . how much flour will she need to make 1 loaf of bread ?\n\nOutput: 2.5\n\n\nInput: Consider Input: the hawks scored 3 touchdowns worth 7 points each . how many points do they have ?\n\n" }, { "from": "gpt", "value": "Output: 21\n\n\n" } ]
[ { "from": "human", "value": "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.\n\n[EX Q]: Title: New Car. Sentence 1: My former coworker Sally needed a new car. Sentence 2: She is a single person living in a house. Sentence 3: She decided to buy a brand new SUV, which she posted on FB. Sentence 4: It cost $25,000. Choices: a. I will not order okra stew again. b. I wanted to comment on her extravagance, but did not.\n[EX A]: b\n\n[EX Q]: Title: Safe Car. Sentence 1: The wife picked a car for her husband. Sentence 2: She bought the safest car she could find. Sentence 3: Her husband was in an accident. Sentence 4: The car saved the husband's life. Choices: a. Caleb fell asleep watching the movie. b. The couple people became lifelong customers of that car company.\n[EX A]: b\n\n[EX Q]: Title: Stanley is Missing. Sentence 1: Stanley went to the park every day to play checkers. Sentence 2: One day he didn't show up. Sentence 3: His friends were worried. Sentence 4: They called Stanley's family to check on him. Choices: a. I didn't get my credits for participating due to early termination. b. Stanley had suffered a fall and was in the hospital.\n[EX A]:" }, { "from": "gpt", "value": "b\n\n" } ]
[ { "from": "human", "value": "Compose 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.\nOne example: original 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 is here: The museum director of the [Science Museum, London] is?\nExplanation: The question is correctly paraphrased in this example.\n\nNow, solve this: original question: Which user profile has [Knowledge Management System] as one of the favorite freebase topics ?\nanswer: systmlabs\nanswer type: User Profile.\nSolution:" }, { "from": "gpt", "value": "Which one of the freebase topics have the user profile [Knowledge Management System]?" } ]
[ { "from": "human", "value": "Construct a question that every answer in the list is correct and reasonable for it.\n--------\nQuestion: study, exercise, play instrument, eat right, care for teeth, work hard, house work\n\nAnswer: name something that you now wish had been forced to do as a child.\n\n\nQuestion: celebrities, band, comedian, tv host, furniture\n\nAnswer: name something you would see on a late-night talk show.\n\n\nQuestion: dog, snake, skunk, frog, mouse\n\nAnswer:" }, { "from": "gpt", "value": "name an animal that's usually not dangerous, but many people are afraid to touch\n\n\n" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nClassify 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.\n\n\"@ozzie_garza: @white_thunduh I'm so sure bitch\" frfr tf\nOutput:" }, { "from": "gpt", "value": "Offensive" } ]
[ { "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: i have no excuse, and no earthly idea why i just decided to piss in the trash can. i'm completely sober, and i've been awake and alert for hours, so it can't be blamed on diminished mental capacity. i just, for some reason, got up from the sofa, went to the trash can, and pissed in it.\n\nmy brain just stopped working.\n" }, { "from": "gpt", "value": "Solution: TIFU by pissing in the trash can in my kitchen" } ]
[ { "from": "human", "value": "Part 1. Definition\nIn this task you will be given two dialogues. You need to determine if both dialogues have the same underlying emotion. The possible emotions are happy, sad, angry, or other. If they do output 'yes', if not output 'no'.\nPart 2. Example\nDialogue 1: 'when did i called u ugly pony when did you ever call fuck u ur rlly a mad person asshole rnda bc'. Dialogue 2: 'go to dhapar math do sl maths a lot of places don't like maths studies it's amazing'.\nAnswer: no\nExplanation: The first dialogue is an angry dialogue and the second dialogue is a happy dialogue. Therefore, they are not the same emotion so the output is 'no'. So this is a good example.\nPart 3. Exercise\nDialogue 1: 'where u added me done but where'. Dialogue 2: 'no it's a great movie i'll have to watch it then stupid ppl like u will not understand it'.\nAnswer:" }, { "from": "gpt", "value": "no" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you're given an article and an answer. Your task is to generate the fill-in-the-blank question for this answer based on the given article. The blanks are always at the end of the question, and can be filled with more than one word or phrase.\n\nArticle: Bell Teacher Campus 2016: Cultural Talks Our talks start at 16:00 on the first week in August, and each one lasts about one hour. Each talk will be offered only once during your 4-day stay. Please sign up on the main Bell Noticeboard (Second floor, Mary Allan Building). August 1st BRITISH MUSIC, by Pete Sharma in Room 106. British music is famous worldwide. In this talk, I'll discuss what's popular and what's not right now and the top music festivals in the UK. We will listen to some of the artists and share some thoughts about singing and dancing. August 2nd LOVE ME, LOVE MY CAT, by Lis Harrison in Room 207. We will be looking at this national interest through idioms , songs, and everyday British life, and along the way covering some vocabulary for \"talking cat\". At the end, we'll be discussing that old topic: do we Brits treat out pets better than we treat our kids? August 3rd A GAME AS ENGLISH AS CROQUET ,by Anna Young in Room 218. First, we will look at the origins of croquet, a much loved garden game in England. We will look at simple croquet rules, and then practice time! We'll go out and play! August 4th WHY ENGLISH PEOPLE LAUGH, by Jim Scrivener in Room 117. Let me try to show you a little bit of what British people find funny. You will discover some of the most popular radio& TV comedy game shows. You probably won't find it funny at all! But you will learn a bit more about us Brits! \n Answer: August 1st\n" }, { "from": "gpt", "value": "If you are interested in the best music festivals in the UK, you may find the talk on _ valuable." } ]
[ { "from": "human", "value": "In 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\n\nExample input: Who were the builders of the mosque in Herat with fire temples ?\nExample output: WP VBD DT NNS IN DT NN IN NNP IN NN NNS .\nExample explanation: This is a good example. All of the POS tags are correct.\nQ: When did the player from Liverpool retire ?\nA:" }, { "from": "gpt", "value": "WRB VBD DT NN IN NNP NN ." } ]
[ { "from": "human", "value": "Given a command in a limited form of natural language, provide the correct sequence of actions that executes the command to thus navigate an agent in its environment. A command can be broken down into many different actions. Actions are uppercase and are individual steps that serve as the building blocks for a command. For commands, 'left' and 'right' are used to denote the direction of an action. The word 'opposite' turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. Actions and commands do not have quotations in the input and output.\n\n[Q]: walk left twice after jump right\n[A]: I_TURN_RIGHT I_JUMP I_TURN_LEFT I_WALK I_TURN_LEFT I_WALK\n\n\n[Q]: walk thrice after run right thrice\n[A]: I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_WALK I_WALK I_WALK\n\n\n[Q]: walk right thrice and jump left thrice\n[A]:" }, { "from": "gpt", "value": "I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_LEFT I_JUMP I_TURN_LEFT I_JUMP I_TURN_LEFT I_JUMP\n\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: You are given a short paragraph, a question and two choices to answer from. Choose the correct answer based on the paragraph and write the answer(not the key).\nProblem:Paragraph: In refraction of light, the greater the change in speed, the more light bends.\n Question: When light travels faster, the light refracting bends \n Choices: A)more \nB)less.\nSolution:" }, { "from": "gpt", "value": "more" } ]
[ { "from": "human", "value": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nGiven a 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\nJacob entered the dining_room. William entered the dining_room. The tomato is in the green_drawer. William exited the dining_room. Jacob moved the tomato to the blue_cupboard. Jacob is in the dining_room. Olivia entered the dining_room. The cucumber is in the blue_cupboard. Olivia exited the dining_room. Jacob moved the cucumber to the green_drawer. William entered the pantry. Jacob entered the pantry. The asparagus is in the red_cupboard. Jacob exited the pantry. Phone rang. William moved the asparagus to the green_pantry. Abigail entered the hall. William entered the hall. The persimmon is in the blue_pantry. William exited the hall. Abigail moved the persimmon to the blue_envelope. Where does Abigail think that William searches for the persimmon?\nSolution: blue_pantry\nWhy? The persimmon was last in the blue_pantry before William exited the hall. After William exited the hall, Abigail moved the persimmon to the blue_envelope, so she knows where William will look for it.\n\nNew input: Logan entered the living_room. Liam entered the living_room. The watermelon is in the green_basket. Logan moved the watermelon to the red_bucket. Abigail entered the study. Evelyn entered the study. The apple is in the blue_cupboard. Abigail moved the apple to the blue_pantry. Abigail entered the den. Liam entered the den. Phone rang. The lime is in the green_crate. Abigail moved the lime to the blue_treasure_chest. Evelyn entered the living_room. Liam entered the living_room. The watermelon is in the red_bucket. Evelyn moved the watermelon to the green_basket. Where does Evelyn think that Liam searches for the watermelon?\nSolution:" }, { "from": "gpt", "value": "green_basket" } ]
[ { "from": "human", "value": "This task is about reading the given passage and construct a question about the information present in the passage. Construct a question in such a way that (i) it is unambiguous, (ii) it is answerable from the passage, (iii) its answer is unique (iv) its answer is a continuous text span from the paragraph. Avoid creating questions that (i) can be answered correctly without actually understanding the paragraph and (ii) uses same words or phrases given in the passage.\n\nQ: The Montana Territory was formed on April 26, 1864, when the U.S. passed the Organic Act. Schools started forming in the area before it was officially a territory as families started settling into the area. The first schools were subscription schools that typically held in the teacher's home. The first formal school on record was at Fort Owen in Bitterroot valley in 1862. The students were Indian children and the children of Fort Owen employees. The first school term started in early winter and only lasted until February 28. Classes were taught by Mr. Robinson. Another early subscription school was started by Thomas Dimsdale in Virginia City in 1863. In this school students were charged $1.75 per week. The Montana Territorial Legislative Assembly had its inaugural meeting in 1864. The first legislature authorized counties to levy taxes for schools, which set the foundations for public schooling. Madison County was the first to take advantage of the newly authorized taxes and it formed fhe first public school in Virginia City in 1886. The first school year was scheduled to begin in January 1866, but severe weather postponed its opening until March. The first school year ran through the summer and didn't end until August 17. One of the first teachers at the school was Sarah Raymond. She was a 25-year-old woman who had traveled to Virginia City via wagon train in 1865. To become a certified teacher, Raymond took a test in her home and paid a $6 fee in gold dust to obtain a teaching certificate. With the help of an assistant teacher, Mrs. Farley, Raymond was responsible for teaching 50 to 60 students each day out of the 81 students enrolled at the school. Sarah Raymond was paid at a rate of $125 per month, and Mrs. Farley was paid $75 per month. There were no textbooks used in the school. In their place was an assortment of books brought in by various emigrants. Sarah quit teaching the following year, but would later become the Madison County superintendent of schools.\n\nA: When was the Montana Territory formed?\n**\nQ: Most light bulbs have either clear or coated glass. The coated glass bulbs have a white powdery substance on the inside called kaolin. Kaolin, or kaolinite, is a white, chalky clay in a very fine powder form, that is blown in and electrostatically deposited on the interior of the bulb. It diffuses the light emitted from the filament, producing a more gentle and evenly distributed light. Manufacturers may add pigments to the kaolin to adjust the characteristics of the final light emitted from the bulb. Kaolin diffused bulbs are used extensively in interior lighting because of their comparatively gentle light. Other kinds of colored bulbs are also made, including the various colors used for \"party bulbs\", Christmas tree lights and other decorative lighting. These are created by coloring the glass with a dopant; which is often a metal like cobalt (blue) or chromium (green). Neodymium-containing glass is sometimes used to provide a more natural-appearing light.\n\nA: What is the powdery substance in coated glass light bulbs?\n\nQ: A perceived turning point was when Blair controversially allied himself with US President George W. Bush in supporting the Iraq War, which caused him to lose much of his political support. The UN Secretary-General, among many, considered the war illegal. The Iraq War was deeply unpopular in most western countries, with Western governments divided in their support and under pressure from worldwide popular protests. The decisions that led up to the Iraq war and its subsequent conduct are currently the subject of Sir John Chilcot's Iraq Inquiry.\n\nA:" }, { "from": "gpt", "value": "Who did Tony Blair side with?\n**\n" } ]
[ { "from": "human", "value": "Given the sentence, generate \"yes, and\" response. \"Yes, and\" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated (\"Yes\") and then expand on that line of thought or context (\"and...\"). 1 In short, a \"Yes, and\" is a dialogue exchange in which a speaker responds by adding new information on top of the information/setting that was constructed by another speaker. Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange, although it could be the case if it agrees with the description above. There are many ways in which a response could implicitly/explicitly agree to the prompt without specifically saying 'yes, and...'. \n\nExample Input: Dr. Brown, why are these two fighters still standing on the scale for their weigh-ins? It's been 20 minutes, already!\nExample Output: Sir, I'm so sorry. I know that the weigh-in line is already out the door. These two contestants seem to be having some sort of face off right here on the scale.\n\nExample Input: Oh, boy did I have a rough day. Can I get a ghost beer please? Thanks.\nExample Output: Hey, I haven't seen you here in awhile. Thought you were a goner.\n\nExample Input: Well, I'm Jims. We made that wish that Freeport would be different, and now it seems to be. I think our wish came true, Gwyneth.\nExample Output:" }, { "from": "gpt", "value": "Either that or we're both dead.\n\n" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you need to count the number of words in a sentence that contain the given letter\n\nSentence: 'a slice of chocolate cake on a plate'. How many words contain the letter 'n' in the sentence.\n" }, { "from": "gpt", "value": "1" } ]
[ { "from": "human", "value": "In this task, you will be given a passage, a question and a list of single-word events identified from the passage. The goal is to point out all events from the given event list that can answer the question. If a question is unanswerable or none of the events answer the question, output should be empty.\nQ: Passage: \"The Palestinian Authority is not functioning in the Gaza Strip, there is no guiding hand,\" Mofaz was quoted as saying by the Yediot Aharonot daily. \"The Palestinian security forces are not obeying the instructions of the PA chairman (Abbas). Question: What happened after Mofaz was quoted? Events: ['functioning', 'is', 'quoted', 'saying', 'obeying']\nA: " }, { "from": "gpt", "value": "" } ]
[ { "from": "human", "value": "In this task you are given a sentence. You must judge whether the main verb of the sentence is in present or past tense. Label the instances as \"Present\" or \"Past\" based on your judgment. If there is no verb in the given text, answer \"Present\".\n\n[EX Q]: \" Happy half birthday. \"\n[EX A]: Present\n\n[EX Q]: The stress of The Program or running no longer cracks the surface of my psyche.\n[EX A]: Present\n\n[EX Q]: She draws a shaky breath.\n[EX A]:" }, { "from": "gpt", "value": "Present\n\n" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task you are given a story and a question regarding that story. You must judge whether the question is answerable based on the info given to you. Label the instances as \"Answerable\" or \"Not Answerable\" based on your judgment. the story and the question are separated by a new line character.\n\nMandy liked two boys at her high school. One boy was cute and popular. The other boy was shy and smart. Mandy spent time with each to make up her mind. She decided to date the shy boy because he was nice.\nWhy did Mandy spend time?\n" }, { "from": "gpt", "value": "Answerable" } ]
[ { "from": "human", "value": "In 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: Handled in this way, the rates might turn out to be 17a and 23a.\nLabel: contradiction.\nGenre: government." }, { "from": "gpt", "value": "The rates will turn out to be 17a no matter what the circumstance." } ]
[ { "from": "human", "value": "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.\n\nEx Input:\nHe's from Rhode Island.\n\nEx Output:\nNo\n\n\nEx Input:\nCostco owners are conservative and therefor evil to the polluted collective called ADN.\n\nEx Output:\nNo\n\n\nEx Input:\nThe decision to file a Petition to Revoke parole or probation--a PTR--is the parole/probation officer's call. The judge can agree to bail but the parole board has the final call: It can either hold the person in prison pending a parole hearing or agree to release them on bail. Either way, being held in jail shouldn't be a death sentence.\n\nEx Output:\n" }, { "from": "gpt", "value": "No\n\n\n" } ]
[ { "from": "human", "value": "Detailed Instructions: In this task, you are given a summary for US Congressional and California state bill, your task is to generate a Title for this bill. The preferred titles are under forty words and mention the purpose of the bill.\nProblem:Children's Hope Act of 2003 - Amends the Internal Revenue Code to provide for a credit ($100, $200 for joint return) which is dependent on enactment of State qualified scholarship tax credits and which is allowed against the Federal income tax for charitable contributions to education investment organizations (as defined by this Act) that provide qualifying assistance for elementary and secondary education.\nSolution:" }, { "from": "gpt", "value": "To amend the Internal Revenue Code of 1986 to provide for a credit which is dependent on enactment of State qualified scholarship tax credits and which is allowed against the Federal income tax for charitable contributions to education investment organizations that provide assistance for elementary and secondary education." } ]
[ { "from": "human", "value": "Instructions: In this task, you are given an adjective, and your job is to generate its antonym. An antonym of a word is a word opposite in meaning to it.\nInput: rich\nOutput:" }, { "from": "gpt", "value": "plain" } ]
[ { "from": "human", "value": "Given the task definition and input, reply with output. Craft one incorrect answer. In doing so, try to use words from the context as much as possible, or by using similar words used in the correct answer. DO NOT craft nonsensical or off-topic incorrect answers, such that the incorrect answers can be directly excluded without reasoning according to the context. Try to make your responses similar to the given correct answer. To this end, try to keep both the length and the style as similar as possible between the correct and the incorrect answer. To make your incorrect answers more difficult, try to incorporate words from context. To avoid being predictable or repetitive, try to add more variations and complexity.\n\nContext: ( yeah , that 's how it tasted to me ) When the dessert came along , we had much fun commenting about the delicacy , and I had much fun laughing at him while he at the orange fruit ( by the side of the plate ) , which had his face distorted into shock and well a face of sourness written all over . Hahaha ... it did n't help that the fruits that were added into the dish was pretty much not in season , not ripe , and all quite sour . Hahaha ... !. \nQuestion: WHat was the reason he did not enjoy dessert ? \nCorrect Answer: The fruit was pretty much not in season .\n" }, { "from": "gpt", "value": "The fruit was pretty much in season and ripe ." } ]
[ { "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: @elchavaloko who cares tbh ones a shitty dirty Argentino & the other is a feather fisted nigger\nOutput:" }, { "from": "gpt", "value": "Hate Speech" } ]
[ { "from": "human", "value": "Given an abstract, indicate which of the provided candidate titles (Option1 and Option2) best describes it (respond with the text of the title, not option1/2).\n\nAbstract: In recent years it has become increasingly apparent that cough is frequently the sign of airway hyperreactivity. While the association between cough and wheezing is well recognized in asthmatics, cough may be the only clinical manifestation of this problem. Emergency physicians frequently have occasion to evaluate the coughing patient. Awareness of this clinical entity should facilitate appropriate evaluation, management, and referral of these patients. \n Which is the apt title for the abstract? option1: Cough variant asthma [published erratum appears in Pediatr Emerg Care 1987 Mar;3(1):9] option2: Prediction and evaluation of brainstem function by auditory brainstem responses in patients with uncal herniation." }, { "from": "gpt", "value": "Cough variant asthma [published erratum appears in Pediatr Emerg Care 1987 Mar;3(1):9]" } ]
[ { "from": "human", "value": "TASK DEFINITION: In this task, You are given an amazon food product review and its summary. Your task is to Generate \"True\" if given review and its summary match, otherwise generate \"False\".\nPROBLEM: There is way to much surgar in this hot chocolate it's like having sugar flavored chocolate, I am going to have to buy some pure powedered chocolate and mix it in the bag, other then that I would say it would taste good if it was not so sweet. \n Summary: Overpowering spices\n\nSOLUTION: False\n\nPROBLEM: Yes people, these things are healthier than the average chip and not only have flavor, but they taste good! I am not a big health food person, I'll take the grease if it makes it taste better. These are 100x better than those baked chips. My brother tried them while he was visiting and liked them so much it was one of the things he asked I mail him while deployed. Only draw back to these chips, they are definitely not for dipping. \n Summary: Healthy and Good, What?!?!\n\nSOLUTION: True\n\nPROBLEM: this is not a review of the product, but the seller/shipper. I ordered this on september 22nd. It is now october 9th and I still have not received the item. \n Summary: Disappointment\n\nSOLUTION:" }, { "from": "gpt", "value": "False\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 will be shown a conversation. You need to write a question with three choices for the conversation. Your question should be answerable based on the conversation and only have one correct answer. Note that you don't need to answer your question. \"W\" and \"M\" in the conversations stand for \"woman\" and \"man\".\n\nM: How about this red dress, Ann? It's very fashionable. W: I don't know. I'm not crazy about red. I think it's a hit too bright for me.\nOutput:" }, { "from": "gpt", "value": "Why doesn't the woman buy the red dress? (A) She thinks it's too crazy to wear red. (B) She thinks red is not fashionable. (C) She thinks red is too bright for her." } ]
[ { "from": "human", "value": "In this task you will be given a list of numbers. A list is shown by two brackets and comma-separated numbers inside, like: [1,2,3]. You should remove all of the even numbers from the list. If every number in the input list is even an empty list should be returned. Zero should be counted as an even number.\n\nEx Input:\n[148, 193, 25, 114, 37, 59]\n\nEx Output:\n[193, 25, 37, 59]\n\n\nEx Input:\n[82, 117, 28, 191, 28, 78]\n\nEx Output:\n[117, 191]\n\n\nEx Input:\n[41, 6, 109, 57, 86, 85, 15, 136]\n\nEx Output:\n" }, { "from": "gpt", "value": "[41, 109, 57, 85, 15]\n\n\n" } ]
[ { "from": "human", "value": "In this task, you are given two statements. The task is to output whether a given textual premise, i.e. Statement 2, entails or implies a given scientific fact, i.e. Statement 1. The output should be 'entails' if Statement 2 supports Statement 1 and should be 'neutral' otherwise.\n\nExample Input: Sentence 1: Creating nature preserves of these activities is most likely to have a positive impact on the environment of earth. Sentence 2: The presentations will focus on the changing nature of recording and communications technologies and how these changes will likely impact the key activities of acquisition, preservation, and access.\nExample Output: neutral\n\nExample Input: Sentence 1: Exact wavelength determines the color of visible light. Sentence 2: It detects infrared wavelengths that are beyond the red light in the rainbow of visible colors.\nExample Output: neutral\n\nExample Input: Sentence 1: The hottest layers are closest to the core of these best describes the relationship between earth's layers. Sentence 2: f) Define the layers of the earth, crust mantle, inner core, outer core.\nExample Output:" }, { "from": "gpt", "value": "neutral\n\n" } ]
[ { "from": "human", "value": "Instructions: In this task, you are given a sentence with a missing word that can be an object, a person, and/or an action. Fill in the blank with a plausible word. Although each sentence has many correct answers, you only have to write one answer.\nInput: PersonX uses PersonX's ___ to prevent\nOutput:" }, { "from": "gpt", "value": "bandage" } ]
[ { "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.\nQ: Tell them you quit to focus on school .\nA: " }, { "from": "gpt", "value": "yes" } ]
[ { "from": "human", "value": "In this task, you're given an input that contains two words, and your task is to predict the correct preposition that connects these two words. Predict the preposition that explicitly conveys both words' meaning, e.g., Word1: king \n Word2: fort: \"king of fort\". Possible prepositions are: \"of\", \"on\", \"in\", \"for\", \"from\", \"about\", and \"with\".\n\n[EX Q]: Word1: earnings \n Word2: dollar\n[EX A]: in\n\n[EX Q]: Word1: broker \n Word2: insurance\n[EX A]: for\n\n[EX Q]: Word1: relief \n Word2: earthquake\n[EX A]:" }, { "from": "gpt", "value": "from\n\n" } ]
[ { "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: Oliver entered the cellar. Sophia entered the cellar. The pineapple is in the blue_container. Sophia exited the cellar. Oliver moved the pineapple to the blue_suitcase. Where was the pineapple at the beginning? Sophia entered the cellar. Aiden entered the cellar. The strawberry is in the blue_suitcase. Sophia moved the strawberry to the blue_container. Where does Sophia think that Aiden searches for the strawberry?\nA: " }, { "from": "gpt", "value": "blue_container" } ]
[ { "from": "human", "value": "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'.\n\nExample Input: Title: Picking Berries. Sentence 1: When he got back someone told him they were poisonous. Sentence 2: He ran into several plants with bright berries. Sentence 3: Larry was camping one day. Sentence 4: Larry had to throw them out. Sentence 5: Larry decided to pick as many as he could carry.\nExample Output: 32514\n\nExample Input: Title: The Painting. Sentence 1: She posed in his studio wearing 1930s fashions. Sentence 2: She had to pose for him for several days. Sentence 3: Thomas asked Gina to pose for a painting. Sentence 4: When the painting was done, Thomas loved it. Sentence 5: He told Gina that it was the best he'd ever done.\nExample Output: 31245\n\nExample Input: 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.\nExample Output:" }, { "from": "gpt", "value": "34125\n\n" } ]
[ { "from": "human", "value": "Definition: In this task, you're given a passage, further information available on a particular linked term from the statement, and a question. Your job is to generate the answer to the question by using the information provided. If there is no clear answer obtainable, output 'none'.\nInput: Passage: Tony Harrison is a communications consultant from Tasmania who has worked in journalism and public relations, marketing and government relations. He is a former political journalist and former press secretary to two Tasmanian Premiers. Tony Harrison was a former corporate affairs manager with the Australian Tourist Commission. He is a former Executive Chairman of Tasmanian public relations, marketing and government relations consultancy, Corporate Communications and was a majority shareholder of the business. Tony Harrison has been involved in providing high-level corporate advice and political lobbying services to clients in Tasmania and Australia, as well as overseeing community consultation programs for the corporate sector and for government. He is the former National President of the Public Relations Institute of Australia (PRIA) and past President of the PRIA in Tasmania. He has won awards for public relations and marketing including a PRIA National Golden Target Gold Award in 2000 and 2003 for government communication. The consultancy has won a National Golden Target Gold award. Tony Harrison was also awarded a special Tasmania Day Award for his service to the public relations profession. Outside the business, Tony Harrison is a Director of Cricket Australia (the former ACB) and former Chairman of Cricket Tasmania, and a member of the Council of the Australian Institute of Company Directors (AICD).\n Link Information: none Question: Which club did Harrison stay at longer?\nOutput:" }, { "from": "gpt", "value": "Answer: none" } ]

Subsets and Splits

No community queries yet

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