[
    {
        "instruction": "In this task you will be given a list of integers. You should only return an integer if the first digit is the same as the last digit in the number. If an integer has a single digit, then it should be returned. If there are no integers that start and end with the same digit then an empty list (\"[]\") should be returned.",
        "input": "[455, 707, 78, 551, 119, -282, 213, -525, -699, -670, -128, -661, -17, 865, 367, -107, 337, -889]",
        "output": "[707, -282, -525]",
        "category": "Program Execution 1000.json"
    },
    {
        "instruction": "In this task you will be given a list of integers. You should round each integer to the nearest tens place. That means you should round the number to the nearest multiple of 10.",
        "input": "[651, 857, -24]",
        "output": "[650, 860, -20]",
        "category": "Program Execution 1001.json"
    },
    {
        "instruction": "In this task you will be given a list of integers. For every element in the list, if the element is positive you should multiply it by 2.  If the element is negative you should multiply it by -3. The output should be a list of integers that is the result of applying that logic to the input list.\n Note: A list is presented with comma separated numbers inside two brackets.",
        "input": "[8, -45, -82]",
        "output": "[16, 135, 246]",
        "category": "Program Execution 1002.json"
    },
    {
        "instruction": "In this task, you need to reverse the order of words in the given sentence.",
        "input": "Sentence: many trucks are being hauled by a train",
        "output": "train a by hauled being are trucks many",
        "category": "Program Execution 1004.json"
    },
    {
        "instruction": "In this task, you need to remove 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.",
        "input": "Sentence: 'a little league plater looking off to the distance'. Remove all words of length '7' in the given sentence.",
        "output": "a little league plater off to the distance",
        "category": "Program Execution 1005.json"
    },
    {
        "instruction": "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.",
        "input": "Sentence: 'a dog looking out the open car window from the drivers seat of a parked car'. Reverse all words of length '2' in the given sentence.",
        "output": "a dog looking out the open car window from the drivers seat fo a parked car",
        "category": "Program Execution 1006.json"
    },
    {
        "instruction": "In this task, you are given a news article. Your task is to classify the article to one out of the four topics 'World', 'Sports', 'Business', 'Sci/Tech' if the article's main topic is relevant to the world, sports, business, and science/technology, correspondingly. If you are not sure about the topic, choose the closest option. Note that URLs in the text have been replaced with [Link].",
        "input": "Teixeira cycles his way to history ARLINGTON -- Rangers first baseman Mark Teixeira made history Tuesday at Ameriquest Field in Arlington against Cleveland when he became the second player in franchise history to hit for the cycle. ",
        "output": "Sports",
        "category": "Text Categorization 1007.json"
    },
    {
        "instruction": "In this task you will be given a passage and a yes/no question based on the passage. You should answer the question using the information from the passage.",
        "input": "passage: A ten-episode first season premiered on Epix on October 16, 2016. On November 17, 2016, Epix renewed Berlin Station for a second season, originally planned to contain ten episodes, which premiered on October 15, 2017 and concluded a nine-episode-season-run on December 3, 2017. On December 6, 2017, Epix renewed the series for a third season that is set to begin production in spring 2018 and premiere sometime in late 2018 or early 2019.\n question: is there a season 3 of berlin station?",
        "output": "Yes",
        "category": "Question Answering 1008.json"
    },
    {
        "instruction": "In this task, you will be presented with a question about part-of-speech tag of a word in the question. You should write the required POS tag answering 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",
        "input": "What is the part-of-speech tag of the word \"European\" in the following question: What Eastern European country was the 1992 European All-around bronze medalist from ?",
        "output": "JJ",
        "category": "Pos Tagging 1010.json"
    },
    {
        "instruction": "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\".",
        "input": "Context: Carson was trying to become a good swimmer. Carson \"went hard or go home\". \n Answer: get the drive to be a good swimmer \n Question: Why did Carson do this?",
        "output": "True",
        "category": "Question Understanding 1012.json"
    },
    {
        "instruction": "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.",
        "input": "Context: Ash was behaving inappropriately at the bar and groped another patron. \n Question: What will happen to Ash? \n Options: (A) make lots of friends (B) be thrown out of the bar (C) separate ash from others",
        "output": "C",
        "category": "Question Answering 1013.json"
    },
    {
        "instruction": "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.",
        "input": "Passage: Despite signs of ongoing distrust, the remaining difficulties were ostensibly swept away by Tuesday's vote which gave Savimbi the right to regular consultations with the president and members of the government and the right to publish messages in the official press. Several deputies from the ruling MPLA have criticised the \"excessive powers\" granted to Savimbi although they followed the party's advice to approve the law. Question: What will happen in the future? Events: ['signs', 'distrust', 'remaining', 'difficulties', 'swept', 'vote', 'gave', 'consultations', 'publish', 'ruling', 'criticised', 'granted', 'followed', 'approve']",
        "output": "publish, consultations",
        "category": "Question Answering 1018.json"
    },
    {
        "instruction": "In this task, you will be shown a Persian passage and question. You need to write a answer for the question. Try to keep your answers as short as possible.",
        "input": "\u0633\u0648\u0634\u06cc \u062e\u0648\u0631\u0627\u06a9\u06cc \u0628\u0631\u0646\u062c\u06cc \u062f\u0631 \u0622\u0634\u067e\u0632\u06cc \u0698\u0627\u067e\u0646\u06cc \u0627\u0633\u062a \u0648 \u0622\u0645\u06cc\u0632\u0647\u200c\u0627\u06cc \u0627\u0633\u062a \u0627\u0632 \u0628\u0631\u0646\u062c \u067e\u062e\u062a\u0647\u0654 \u0698\u0627\u067e\u0646\u06cc \u0628\u0627 \u0686\u0627\u0634\u0646\u06cc \u0633\u0631\u06a9\u0647\u060c \u0686\u0646\u062f\u06cc\u0646 \u06af\u0648\u0646\u0647 \u062e\u0648\u0631\u0627\u06a9 \u062f\u0631\u06cc\u0627\u06cc\u06cc (\u0628\u06cc\u0634\u062a\u0631 \u062e\u0627\u0645)\u060c \u0633\u0628\u0632\u06cc\u062c\u0627\u062a \u0648 \u062a\u062e\u0645 \u0645\u0631\u063a \u06a9\u0647 \u0628\u0647 \u0635\u0648\u0631\u062a \u0633\u0631\u062f \u062e\u0648\u0631\u062f\u0647 \u0645\u06cc\u200c\u0634\u0648\u062f. \u062f\u0631 \u0622\u063a\u0627\u0632\u060c \u0633\u0648\u0634\u06cc \u062a\u0646\u0647\u0627 \u0631\u0648\u0634\u06cc \u0628\u0631\u0627\u06cc \u0646\u06af\u0647\u062f\u0627\u0631\u06cc \u0645\u0627\u0647\u06cc \u0628\u0648\u062f \u06a9\u0647 \u062f\u0631 \u0622\u0633\u06cc\u0627\u06cc \u0634\u0631\u0642\u06cc \u0631\u0648\u0627\u062c \u062f\u0627\u0634\u062a \u0648\u0644\u06cc \u067e\u0633 \u0627\u0632 \u0631\u0627\u0647 \u06cc\u0627\u0641\u062a\u0646 \u0628\u0647 \u0686\u06cc\u0646\u060c \u0648\u0627\u0631\u062f \u0641\u0631\u0647\u0646\u06af \u063a\u0630\u0627\u06cc\u06cc \u06a9\u0634\u0648\u0631 \u0698\u0627\u067e\u0646 \u0634\u062f. \u0633\u0648\u0634\u06cc \u06af\u0648\u0646\u0647\u200c\u0647\u0627\u06cc \u0641\u0631\u0627\u0648\u0627\u0646\u06cc \u062f\u0627\u0631\u062f \u0648\u0644\u06cc \u0627\u0645\u0631\u0648\u0632\u0647 \u062f\u0631 \u0646\u0632\u062f \u0639\u0645\u0648\u0645 \u0645\u0631\u062f\u0645\u060c \u0646\u0627\u0645 \u0633\u0648\u0634\u06cc \u0627\u0634\u0627\u0631\u0647\u200c\u06a9\u0646\u0646\u062f\u0647 \u0628\u0647 \u062a\u0646\u0647\u0627 \u06cc\u06a9\u06cc \u0627\u0632 \u06af\u0648\u0646\u0647\u200c\u0647\u0627\u06cc \u0627\u06cc\u0646 \u062e\u0627\u0646\u0648\u0627\u062f\u0647\u0654 \u063a\u0630\u0627\u06cc\u06cc\u060c \u0633\u0648\u0634\u06cc \u0627\u062f\u0648 \u0627\u0633\u062a. \u062f\u0631 \u0627\u06cc\u0646 \u06af\u0648\u0646\u0647 \u0627\u0632 \u0633\u0648\u0634\u06cc \u0628\u0631 \u0631\u0648\u06cc \u06cc\u06a9 \u0642\u0637\u0639\u0647\u0654 \u0628\u0631\u0646\u062c\u06cc \u0628\u06cc\u0636\u06cc\u200c\u0645\u0627\u0646\u0646\u062f\u060c \u0628\u0631\u0634 \u0646\u0627\u0632\u06a9\u06cc \u0627\u0632 \u0645\u0627\u0647\u06cc \u06af\u0630\u0627\u0634\u062a\u0647 \u0645\u06cc\u200c\u0634\u0648\u062f. \u0645\u0627\u0647\u06cc\u060c \u062a\u0648\u0641\u0648 (\u0641\u0631\u0627\u0648\u0631\u062f\u0647\u0654 \u0633\u0648\u06cc\u0627)\u060c \u062e\u0648\u0631\u0627\u06a9 \u062f\u0631\u06cc\u0627\u06cc\u06cc\u060c \u062a\u062e\u0645\u200c\u0645\u0631\u063a \u0648 \u062f\u06cc\u06af\u0631 \u062e\u0648\u0631\u0627\u06a9\u06cc\u200c\u0647\u0627\u06cc \u0628\u06a9\u0627\u0631 \u0631\u0641\u062a\u0647 \u062f\u0631 \u067e\u064f\u0631 \u06a9\u0631\u062f\u0646 \u0633\u0648\u0634\u06cc\u060c \u0647\u0645\u06af\u06cc \u0633\u0631\u0634\u0627\u0631 \u0627\u0632 \u067e\u0631\u0648\u062a\u0626\u06cc\u0646 \u0647\u0633\u062a\u0646\u062f. \u0639\u0644\u0627\u0648\u0647 \u0628\u0631 \u0622\u0646 \u0645\u06cc\u200c\u062a\u0648\u0627\u0646 \u0648\u06cc\u062a\u0627\u0645\u06cc\u0646 \u0648 \u0645\u0648\u0627\u062f \u0645\u0639\u062f\u0646\u06cc \u0631\u0627 \u0646\u06cc\u0632 \u062f\u0631 \u062e\u0648\u0631\u0627\u06a9\u200c\u0647\u0627\u06cc \u062f\u0631\u06cc\u0627\u06cc\u06cc \u0648 \u0633\u0628\u0632\u06cc\u062c\u0627\u062a \u0633\u0648\u0634\u06cc \u067e\u06cc\u062f\u0627 \u06a9\u0631\u062f. \u0633\u0648\u0634\u06cc \u0628\u06cc\u0634\u062a\u0631 \u0647\u0645\u0631\u0627\u0647 \u0628\u0627 \u0686\u0627\u0634\u0646\u06cc \u0633\u0633 \u0633\u0648\u06cc\u0627 \u062e\u0648\u0631\u062f\u0647 \u0645\u06cc\u200c\u0634\u0648\u062f. \u0628\u0647\u062a\u0631\u06cc\u0646 \u0631\u0648\u0634 \u0628\u0631\u0627\u06cc \u0636\u062f\u0639\u0641\u0648\u0646\u06cc \u0645\u0648\u0627\u062f \u063a\u0630\u0627\u06cc\u06cc \u067e\u062e\u062a\u0646 \u0645\u0648\u0627\u062f \u0627\u0633\u062a \u0627\u0645\u0627 \u0627\u06cc\u0646 \u0631\u0648\u0634 \u062f\u0631 \u0633\u0648\u0634\u06cc \u0628\u06a9\u0627\u0631 \u0628\u0631\u062f\u0647 \u0646\u0645\u06cc\u200c\u0634\u0648\u062f. \n Question: \u0633\u0648\u0634\u06cc \u0627\u0632 \u0646\u0638\u0631 \u0627\u0631\u0632\u0634 \u063a\u0630\u0627\u06cc\u06cc \u0686\u0647 \u06af\u0648\u0646\u0647 \u0627\u0633\u062a\u061f",
        "output": "\u0633\u0631\u0634\u0627\u0631 \u0627\u0632 \u067e\u0631\u0648\u062a\u0626\u06cc\u0646 \u0647\u0633\u062a\u0646\u062f. \u0639\u0644\u0627\u0648\u0647 \u0628\u0631 \u0622\u0646 \u0645\u06cc\u200c\u062a\u0648\u0627\u0646 \u0648\u06cc\u062a\u0627\u0645\u06cc\u0646 \u0648 \u0645\u0648\u0627\u062f \u0645\u0639\u062f\u0646\u06cc \u0631\u0627 \u0646\u06cc\u0632 \u062f\u0631 \u062e\u0648\u0631\u0627\u06a9\u200c\u0647\u0627\u06cc \u062f\u0631\u06cc\u0627\u06cc\u06cc \u0648 \u0633\u0628\u0632\u06cc\u062c\u0627\u062a \u0633\u0648\u0634\u06cc \u067e\u06cc\u062f\u0627 \u06a9\u0631\u062f",
        "category": "Question Answering 1023.json"
    },
    {
        "instruction": "In this task, you will be shown a Persian passage and a question, and you have to determine whether the question is answerable based on the passage or not. If the question is answerable, choose the \"True\" label, and if not select \"False\"",
        "input": "\u0647\u0631\u06cc \u06af\u0648\u0631\u062f\u0648\u0646 \u0641\u0631\u0627\u0646\u06a9\u0641\u0648\u0631\u062a (\u0632\u0627\u062f\u0647\u0654 \u06f2\u06f9 \u0645\u0647 \u06f1\u06f9\u06f2\u06f9) \u0641\u06cc\u0644\u0633\u0648\u0641\u0650 \u0622\u0645\u0631\u06cc\u06a9\u0627\u06cc\u06cc \u0627\u0633\u062a. \u062d\u0648\u0632\u0647\u200c\u0647\u0627\u06cc\u0650 \u0627\u0635\u0644\u06cc\u0650 \u0641\u0639\u0627\u0644\u06cc\u062a\u0650 \u0627\u0648\u060c \u0645\u0631\u0628\u0648\u0637 \u0628\u0647 \u0641\u0644\u0633\u0641\u0647\u0654 \u0630\u0647\u0646\u060c \u0641\u0644\u0633\u0641\u0647\u0654 \u0627\u062e\u0644\u0627\u0642\u060c \u0646\u0638\u0631\u06cc\u0647\u0654 \u06a9\u0646\u0634 \u0648 \u062e\u0631\u062f\u06af\u0631\u0627\u06cc\u06cc \u0642\u0631\u0646\u0650 \u06f1\u06f7\u0645 \u0627\u0633\u062a. \u0645\u0642\u0627\u0644\u0647\u0654 \u06f1\u06f9\u06f8\u06f6 \u0627\u0648 \u0628\u0627 \u0646\u0627\u0645\u0650 \u062f\u0631 \u0628\u0627\u0628 \u0645\u0632\u062e\u0631\u0641\u200c\u06af\u0648\u06cc\u06cc\u060c \u067e\u0698\u0648\u0647\u0634\u06cc \u0641\u0644\u0633\u0641\u06cc \u062f\u0631\u0628\u0627\u0631\u0647\u0654 \u0645\u0641\u0647\u0648\u0645\u0650 \u00ab\u062d\u0631\u0641\u0650 \u0645\u0632\u062e\u0631\u0641\u00bb \u0627\u0633\u062a \u06a9\u0647 \u0686\u0627\u067e\u0650 \u0622\u0646 \u0628\u0647 \u0635\u0648\u0631\u062a\u0650 \u06a9\u062a\u0627\u0628 \u062f\u0631 \u0633\u0627\u0644\u0650 \u06f2\u06f0\u06f0\u06f5 \u0645\u06cc\u0644\u0627\u062f\u06cc \u0628\u0647 \u0634\u06a9\u0644\u0650 \u0639\u062c\u06cc\u0628\u06cc \u067e\u0631\u0641\u0631\u0648\u0634 \u0634\u062f \u0648 \u0628\u0627\u0639\u062b\u0650 \u0634\u0647\u0631\u062a\u0650 \u0631\u0633\u0627\u0646\u0647\u200c\u0627\u06cc\u0650 \u0627\u0648 \u0634\u062f. \u062f\u0631 \u0633\u0627\u0644\u0650 \u06f2\u06f0\u06f0\u06f6\u060c \u0627\u0648 \u06a9\u062a\u0627\u0628\u06cc \u0645\u0631\u062a\u0628\u0637 \u0628\u0627 \u0646\u0627\u0645\u0650 \u00ab\u062f\u0631\u0628\u0627\u0631\u0647\u0654 \u062d\u0642\u06cc\u0642\u062a\u00bb \u0645\u0646\u062a\u0634\u0631 \u06a9\u0631\u062f \u06a9\u0647 \u0645\u0648\u0636\u0648\u0639\u0650 \u0622\u0646 \u0627\u0632 \u0628\u06cc\u0646 \u0631\u0641\u062a\u0646\u0650 \u0628\u0647\u0627\u06cc\u0650 \u062d\u0642\u06cc\u0642\u062a \u062f\u0631 \u0646\u0632\u062f\u0650 \u062c\u0627\u0645\u0639\u0647 \u0628\u0648\u062f. \u0627\u0645\u0627 \u062f\u0631 \u0628\u06cc\u0646\u0650 \u0641\u06cc\u0644\u0633\u0648\u0641\u0627\u0646\u060c \u0634\u0647\u0631\u062a\u0650 \u0641\u0631\u0627\u0646\u0641\u06a9\u0648\u0631\u062a \u0628\u06cc\u0634 \u0627\u0632 \u0647\u0645\u0647 \u0628\u0647 \u062e\u0627\u0637\u0631\u0650 \u062a\u0641\u0633\u06cc\u0631 \u0627\u0648 \u0627\u0632 \u0627\u0646\u062f\u06cc\u0634\u0647\u200c\u0647\u0627\u06cc\u0650 \u062f\u06a9\u0627\u0631\u062a \u0648 \u0647\u0645\u0686\u0646\u06cc\u0646 \u062f\u0641\u0627\u0639\u0650 \u0627\u0648 \u0627\u0632 \u0627\u062e\u062a\u06cc\u0627\u0631 \u0648 \u0627\u0631\u0627\u062f\u0647\u0654 \u0622\u0632\u0627\u062f \u0627\u0633\u062a \n Question: \u0647\u0631\u06cc \u0641\u0631\u0627\u0646\u06a9\u0641\u0648\u0631\u062a \u062f\u0631 \u06a9\u062f\u0627\u0645 \u06a9\u0634\u0648\u0631 \u0645\u062a\u0648\u0644\u062f \u0634\u062f\u0647\u061f",
        "output": "True",
        "category": "Answerability Classification 1024.json"
    },
    {
        "instruction": "In this task you are given a sentence pair from wikipedia that have high lexical overlap. If the sentences have the same meaning and are just paraphrases of each other label them as \"Paraphrase\" , if not label them as \"Not paraphrase\". The two sentences are seperated by a new line.",
        "input": "David Spinozza plays the acoustic guitar in the song , Liberty DeVitto plays the drums and Robert Freedman the horn and string orchestration .\nDavid David Spinozza plays the acoustic guitar in the song , Liberty DeVitto plays the drums and Robert Freedman plays the horn and string orchestration .",
        "output": "Paraphrase",
        "category": "Text Matching 1028.json"
    },
    {
        "instruction": "In this task you are given a statement and an explanation giving you further knowledge about an entity in the statement. You must judge whether the statement is true or false based on the explanation. Label an instance as \"True\" if the explanation confirms the statement or doesn't disprove it. Label an instance as \"False\" if the explanation disproves the statement. The statement and explanation are separated by a newline character.",
        "input": "Vitamin C does not occur naturally, and must be synthesized in a lab.\nThis is clearly untrue, as it's necessary for most animals to survive.",
        "output": "False",
        "category": "Fact Verification 1031.json"
    },
    {
        "instruction": "Given a sentence in French, generate a new French sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.",
        "input": "Ma voiture en panne vous donnerait envie de vider l'appartement.",
        "output": "Ma voiture en panne vous ferait jurer de prendre le bus., Ma voiture en panne vous ferait vouloir blesser le pneu., Ma panne de voiture vous ferait prendre le bus., Ma voiture en panne vous ferait vouloir ha\u00efr la nation.",
        "category": "Sentence Perturbation 1034.json"
    },
    {
        "instruction": "Given a sentence in Hindi, generate a new Hindi sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.",
        "input": "\u0906\u092a \u090f\u0915 \u0928\u094c\u0915\u0930\u0940 \u0916\u0930\u0940\u0926\u0928\u0947 \u0915\u0947 \u0932\u093f\u090f \u091a\u093e\u0939\u0924\u0947 \u0939\u0948\u0902 \u0924\u094b \u0906\u092a \u090f\u0915 \u092e\u0949\u0921\u0932 \u0915\u0947 \u0932\u093f\u090f \u0906\u0926\u0947\u0936 \u0915\u0930\u0928\u093e \u091a\u093e\u0939\u093f\u090f.",
        "output": "\u092f\u0926\u093f \u0906\u092a \u090f\u0915 \u0936\u0930\u094d\u091f \u0916\u0930\u0940\u0926\u0928\u0947 \u0915\u0940 \u092f\u093e\u0926 \u0906\u0924\u0940 \u0939\u0948 \u0924\u094b \u0906\u092a \u090f\u0915 \u0917\u0948\u0930\u0947\u091c \u0915\u0947 \u0932\u093f\u090f \u0915\u0930\u0928\u093e \u091a\u093e\u0939\u093f\u090f., \u0906\u092a \u090f\u0915 \u0936\u0930\u094d\u091f \u0916\u0930\u0940\u0926\u0928\u0947 \u0915\u0947 \u0932\u093f\u090f \u091a\u093e\u0939\u0924\u0947 \u0939\u0948\u0902 \u0924\u094b \u0906\u092a \u090f\u0915 \u0926\u0941\u0915\u093e\u0928 \u0915\u0947 \u0932\u093f\u090f \u091c\u093e\u0928\u093e \u091a\u093e\u0939\u093f\u090f\u0964, \u0906\u092a \u090f\u0915 \u0915\u094b\u091f \u0916\u0930\u0940\u0926\u0928\u0947 \u0915\u0947 \u0932\u093f\u090f \u0915\u0930\u0928\u093e \u091a\u093e\u0939\u0924\u0947 \u0939\u0948\u0902 \u0924\u094b \u0906\u092a \u090f\u0915 \u0915\u0935\u0930 \u092e\u0947\u0902 \u0924\u0948\u0930 \u091a\u093e\u0939\u093f\u090f., \u0905\u0917\u0930 \u0906\u092a \u090f\u0915 \u0915\u093e\u0930\u094d\u0921 \u0915\u0940\u0932 \u0915\u0930\u0928\u0947 \u0915\u0940 \u0915\u094b\u0936\u093f\u0936 \u0915\u0930\u0924\u0947 \u0939\u0948\u0902 \u0924\u094b \u0906\u092a\u0915\u094b \u090f\u0915 \u0926\u0941\u0915\u093e\u0928 \u092e\u0947\u0902 \u091c\u093e\u0928\u093e \u091a\u093e\u0939\u093f\u090f.",
        "category": "Sentence Perturbation 1035.json"
    },
    {
        "instruction": "Given a sentence in Italian, generate a new Italian sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.",
        "input": "Se si desidera hackerare un contratto allora si dovrebbe avere una penna.",
        "output": "Se volete firmare una protesta allora dovreste avere una penna., Se si decide di firmare una matita allora si dovrebbe avere una penna., Se si desidera spendere un contratto allora si dovrebbe avere una penna., Se si desidera firmare un contratto allora si dovrebbe avere una penna.",
        "category": "Sentence Perturbation 1036.json"
    },
    {
        "instruction": "Given a sentence in Dutch, generate a new Dutch sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.",
        "input": "Als je rijst wilt overslaan dan moet je meer water drinken.",
        "output": "Als u dreigt om gewicht te verliezen dan moet u meer water drinken., Als u wilt afvallen dan moet u meer water drinken., Als u wilt gewicht frituren dan moet u meer water drinken., Als u lijdt om gewicht te verliezen dan moet u meer water drinken.",
        "category": "Sentence Perturbation 1037.json"
    },
    {
        "instruction": "Given a sentence in Russian, generate a new Russian sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.",
        "input": "\u041c\u0435\u0441\u0442\u043e, \u0433\u0434\u0435 \u043c\u043e\u0436\u043d\u043e \u0431\u0440\u043e\u0441\u0430\u0442\u044c \u0435\u0434\u0443.",
        "output": "\u041c\u0435\u0441\u0442\u043e, \u0433\u0434\u0435 \u043c\u043e\u0436\u043d\u043e \u043f\u043e\u0435\u0441\u0442\u044c., \u041c\u0435\u0441\u0442\u043e, \u0433\u0434\u0435 \u043c\u043e\u0436\u043d\u043e \u0436\u0430\u0440\u0438\u0442\u044c \u0435\u0434\u0443., \u041c\u0435\u0441\u0442\u043e, \u0433\u0434\u0435 \u043c\u043e\u0436\u043d\u043e \u043a\u0443\u043f\u0438\u0442\u044c \u0435\u0434\u0443., \u041c\u0435\u0441\u0442\u043e, \u0433\u0434\u0435 \u043c\u043e\u0436\u043d\u043e \u043f\u043e\u0441\u0442\u0438\u0442\u044c \u0435\u0434\u0443.",
        "category": "Sentence Perturbation 1038.json"
    },
    {
        "instruction": "Given a sentence in Vietnamese, generate a new Vietnamese sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.",
        "input": "T\u1ed5ng th\u1ed1ng c\u00f3 th\u1ec3 th\u1ed1ng tr\u1ecb c\u1ea3 n\u01b0\u1edbc.",
        "output": "T\u1ed5ng th\u1ed1ng c\u00f3 th\u1ec3 th\u00e0nh l\u1eadp l\u1ef1c l\u01b0\u1ee3ng., T\u1ed5ng th\u1ed1ng c\u00f3 th\u1ec3 trao \u0111\u1ed5i ti\u1ec1n m\u1eb7t., T\u1ed5ng th\u1ed1ng c\u00f3 th\u1ec3 th\u1ecfa thu\u1eadn vi\u1ec7c gi\u1ea3i c\u1ee9u., T\u1ed5ng th\u1ed1ng c\u00f3 th\u1ec3 ph\u1ee5 tr\u00e1ch ban.",
        "category": "Sentence Perturbation 1039.json"
    },
    {
        "instruction": "Given a sentence in Chinese, generate a new Chinese sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.",
        "input": "\u5e3d\u5b50\u5728\u4f60\u7684\u624b\u8868\u94fe\u4e0a",
        "output": "\u8fd0\u52a8\u5728\u4f60\u5988\u5988\u7684\u65e5\u5e38\u751f\u6d3b\u4e2d\u8fdb\u884c\u3002, \u5e3d\u5b50\u9876\u5728\u4f60\u5934\u4e0a, \u5e3d\u5b50\u4f1a\u51fa\u73b0\u5728\u4f60\u7684\u4e50\u961f\u540d\u5355\u4e0a, \u5e3d\u5b50\u957f\u5728\u4f60\u5934\u4e0a",
        "category": "Sentence Perturbation 1040.json"
    },
    {
        "instruction": "Given a sentence, generate a new sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.",
        "input": "A switch can course through a ribbon .",
        "output": "A patient can course through a meditation ., A river can course through a valley., A compass can course through a paragraph ., A candidate can course through a lifetime .",
        "category": "Sentence Perturbation 1041.json"
    },
    {
        "instruction": "Given a sentence in Arabic, generate a new Arabic sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.",
        "input": "\u0633\u0644\u0627\u062d \u064a\u0633\u062a\u062e\u062f\u0645 \u0644\u0644\u0642\u062a\u0627\u0644.",
        "output": "\u062a\u064f\u0633\u062a\u062e\u062f\u0645 \u062f\u0631\u0627\u062c\u0629 \u0646\u0627\u0631\u064a\u0629 \u0644\u0644\u0642\u062a\u0627\u0644., \u00ab \u0625\u0646 \u00bb \u0645\u062e\u0641\u0641\u0629 \u0645\u0646 \u0627\u0644\u062b\u0642\u064a\u0644\u0629 \u0648\u0627\u0633\u0645\u0647\u0627 \u0645\u062d\u0630\u0648\u0641 \u060c \u0623\u064a \u0625\u0646\u0647 \u00ab \u0635\u064f\u0641\u0651\u0650\u0631 \u00bb \u0623\u064a \u0627\u0644\u0648\u0644\u062f \u00ab \u0644\u0644\u0645\u0642\u0627\u062a\u0644\u064a\u0646 \u00bb., \u062a\u064f\u0633\u062a\u062e\u062f\u0645 \u0637\u0627\u0626\u0631\u0629 \u0647\u0644\u064a\u0643\u0648\u0628\u062a\u0631 \u0644\u0644\u0642\u062a\u0627\u0644., \u064a\u064f\u0642\u0652\u0628\u064e\u0644\u064f \u0633\u0644\u0627\u062d \u0644\u0644\u0642\u062a\u0627\u0644.",
        "category": "Sentence Perturbation 1042.json"
    },
    {
        "instruction": "Given a sentence in Bulgarian, generate a new Bulgarian sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.",
        "input": "\u0418 \u043d\u0438\u043c\u0430 \u043f\u0440\u0438 \u0432\u0430\u0441 \u0438\u043c\u0430 \u043b\u0438\u0441\u0442\u0430 \u043e\u0442 \u0434\u044a\u0440\u0432\u0435\u0442\u0430?",
        "output": "\u0418 \u043d\u0438\u043c\u0430 \u0442\u0430\u043c \u0449\u0435 \u043e\u0442\u043a\u0440\u0438\u0435\u0448 \u0440\u0435\u043a\u0430 \u0441\u0440\u0435\u0434 \u0434\u044a\u0440\u0432\u0435\u0442\u0430\u0442\u0430?, \u0418 \u0449\u0435 \u043e\u0442\u043a\u0440\u0438\u0435\u0448 \u0442\u0438 [ \u043e, \u041c\u0443\u0445\u0430\u043c\u043c\u0430\u0434 ], \u0447\u0435 \u043d\u0430 \u0434\u044a\u0440\u0432\u0435\u0442\u0430\u0442\u0430 \u0438\u043c\u0430 \u0440\u0443\u0445\u0432\u0430\u043d\u0435., \u041d\u0430\u0439-\u0432\u0435\u0440\u043e\u044f\u0442\u043d\u043e \u0449\u0435 \u043d\u0430\u043c\u0435\u0440\u0438\u0442\u0435 \u043b\u0438\u0441\u0442\u043e \u0432 \u0434\u044a\u0440\u0432\u0435\u0442\u0430\u0442\u0430., \u0418 \u043a\u043e\u043b\u043a\u043e \u0433\u043e\u043b\u044f\u043c\u043e \u0435 \u043e\u043d\u043e\u0432\u0430, \u043f\u043e \u043a\u043e\u0435\u0442\u043e \u043c\u043e\u0436\u0435\u0448 \u0434\u0430 \u043d\u0430\u043c\u0435\u0440\u0438\u0448 \u043a\u043b\u043e\u043d\u0438 \u043f\u043e \u0434\u044a\u0440\u0432\u0435\u0442\u0430\u0442\u0430!",
        "category": "Sentence Perturbation 1043.json"
    },
    {
        "instruction": "Given a sentence in German, generate a new German sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.",
        "input": "Du bist verr\u00fcckt, ein Silberk\u00fcken in einem Adlernest zu finden.",
        "output": "Sie neigen dazu, einen Scip in einem Adlernest zu finden., Sie sind ungl\u00fccklich, einen Glatzenadler in einem Adlernest zu finden., Sie sind traurig, einen Glatzadler in einem Aide's Weg zu finden., Du wirst wahrscheinlich einen Glatzenadler in einem Adlernest finden.",
        "category": "Sentence Perturbation 1044.json"
    },
    {
        "instruction": "Given a sentence in Spanish, generate a new Spanish sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.",
        "input": "La gente parece llorar comida todos los d\u00edas para vivir.",
        "output": "La gente necesita comer todos los d\u00edas para vivir., los seres humanos necesitan comer alimentos todos los d\u00edas para consumir., La gente hace a los alimentos b\u00e1sicos todos los d\u00edas para vivir., La gente lucha para comer toda necesidad de vivir.",
        "category": "Sentence Perturbation 1045.json"
    },
    {
        "instruction": "Given a sentence and an entity, the task is to select the authors sentiment towards the enity. Sentiments can be Positive, Neutral and Negative. Select Positive if the sentence expresses a positive view towards the given entity or praises its quality or skills. Select Neutral if the sentence expresses no clear view towards the entity or has equal amounts of positive and negative statements or expressing some fact/quote by someone else. Select Negative if the sentence expresses a negative view towards like harsh remarks, criticizing entities action/decision etc. Note that URLs in the text have been replaced with [Link].",
        "input": "What is the sentiment of the following document towards the entity Mariano Rajoy ? In an interview with Spanish newspaper El Pais on Saturday  Rajoy  was asked if  he  was ready to trigger the article 155 of the constitution  and said: \u00e2\u0080\u009cI don\u00e2\u0080\u0099t rule out absolutely anything that is within the law ... Ideally  it shouldn\u00e2\u0080\u0099t be necessary to implement extreme solutions but for that not to happen things would have to be changed.\u00e2\u0080\u009d",
        "output": "Neutral",
        "category": "Sentiment Analysis 1049.json"
    },
    {
        "instruction": "Given a sentence, an entity and its sentiment towards the entity, verify if it is the correct sentiment towards the entity. Answer should be yes or no. Note that URLs in the text have been replaced with [Link].",
        "input": "Verify if the sentiment of the following document towards the entity Rodrigo Duterte is Negative . Western governments and human rights watchdogs have expressed alarm over  his  crackdown on illegal drugs  which has left thousands of mostly poor suspects dead.  He  has lashed out at critics  including European governments  which  he  told Monday \"to go to hell\" for imposing conditions on financial aid.",
        "output": "yes",
        "category": "Sentiment Analysis 1050.json"
    },
    {
        "instruction": "Given a document, an entity and its sentiment towards the entity, verify if it is the correct sentiment towards the entity. Answer should be yes or no. Note that URLs in the text have been replaced with [Link].",
        "input": "Verify if the sentiment of the following document towards the entity David Samson is Negative . Miami Marlins president David Samson  will reportedly be shown the door after the team is sold. That should make it much easier for the incoming owners to bolster the team's balance sheet.\nBut equity has been hard to come by in this sale process. As things stand  the asking price for the team --the sale of which has been led by  Samson  -- has fallen from $1.8 billion to $1.2 billion in just about eight months.\nCurrent Marlins owner Jeff Loria and  Samson  have built up a lot of ill will in Miami over the years  mostly due to the stadium boondoggle that led to the recall of Miami-Dade mayor Carlos Alvarez. The Marlins are last in the National League in attendance.\nWith  Samson  on  his  way out  more cash should come in. And with the team expected to lose money the next few years  that cash will come in handy. Rebuilding the brand is not going to be cheap.",
        "output": "no",
        "category": "Sentiment Analysis 1051.json"
    },
    {
        "instruction": "In this task, you are given a sentence in the English language and your task is to convert it into the Hindi language. In the translation, keep numbers as it is and make it sentence case (capitalize only the first word of each sentence and noun).",
        "input": "\u092a\u094d\u0930\u0903 \u092f\u0942\u091f\u0940\u0906\u0907 \u0928\u0947 \u0930\u093f\u0932\u092f\u0902\u0938 \u0915\u0947 \u0936\u0947\u092f\u0930 \u0938\u0940\u0927\u0947 \u092c\u093e\u091c\u093e\u0930 \u0938\u0947 \u0909 \u0906\u0928\u0947 \u0915\u0947 \u092c\u0926\u0932\u0947 \u092a\u094d\u0930\u093e\u0907\u0935\u0947\u091f \u092a\u094d\u0932\u0947\u0938\u092e\u0947\u0902\u091f \u0915\u0947 \u091c\u0930\u093f\u090f \u0915\u094d\u092f\u094b\u0902 \u0916\u0930\u0940\u0926\u0947 ?",
        "output": "Q . Why did UTI buy RIL shares through private placement and not from the market ?",
        "category": "Translation 1052.json"
    },
    {
        "instruction": "In this task, you are given a sentence in the English language and your task is to convert it into the Hindi language. In translation, keep numbers as it is.",
        "input": "Due to the curse of Guru Parshuram finding himself unable to use divine weapons he gets down to extract the wheel of the chariot.",
        "output": "\u0917\u0941\u0930\u0941 \u092a\u0930\u0936\u0941\u0930\u093e\u092e \u0915\u0947 \u0936\u093e\u092a \u0915\u0947 \u0915\u093e\u0930\u0923 \u0935\u0939 \u0905\u092a\u0928\u0947 \u0915\u094b \u0926\u0948\u0935\u0940\u092f \u0905\u0938\u094d\u0924\u094d\u0930\u094b\u0902 \u0915\u0947 \u092a\u094d\u0930\u092f\u094b\u0917 \u092e\u0947\u0902 \u092d\u0940 \u0905\u0938\u092e\u0930\u094d\u0925 \u092a\u093e\u0915\u0930 \u0930\u0925 \u0915\u0947 \u092a\u0939\u093f\u090f \u0915\u094b \u0928\u093f\u0915\u093e\u0932\u0928\u0947 \u0915\u0947 \u0932\u093f\u090f \u0928\u0940\u091a\u0947 \u0909\u0924\u0930\u0924\u093e \u0939\u0948\u0964",
        "category": "Translation 1053.json"
    },
    {
        "instruction": "In this task, you are given a sentence in the Hindi language and a corresponding English translation of the Hindi sentence. Your task is to generate a label \"Yes\" if the translation is correct, otherwise generate label \"No\". In the translation, English sentence should preserve the number as it is and it should be in sentence case (capitalize only the first word of each sentence and noun).",
        "input": "Hindi: \u0910\u0938\u093e \u0932\u0917\u0924\u093e \u0939\u0948 \u091c\u0948\u0938\u0947 \u092e\u0948\u0902 \u092a\u094b\u0936\u093e\u0915\u094b \u0915\u0947 \u0938\u093e\u0925 \u0916\u0947\u0932 \u0930\u0939\u0940 \u0939\u0942\u0901 , \n English: Puzzling Procastrination : In this atmosphere of contempt for the law and growing anarchy , it becomes even more puzzling that the home minister has not yet begun to address the issue of police reform .",
        "output": "No",
        "category": "Text Matching 1054.json"
    },
    {
        "instruction": "In this task, you are given a sentence which is either in the Hindi language or English language. You task is to identify the language of input sentence. Input sentence can be in Hindi or English language only and also it cannot have two languages at a time.",
        "input": "all his books were translated to English and Urdu, and other languages like Chinese, Russian, etc and his stories were published in other foreign languages.",
        "output": "English",
        "category": "Language Identification 1055.json"
    },
    {
        "instruction": "In this task you are given a sentence. You must judge whether there exist two consecutive words within the sentence with flipped orders, that is, whether the sentence will make sense and be correct if the order of two consecutive words changes. Label the instances as \"Inversion\" or \"Original\" based on your judgment.",
        "input": "One final hard thrust and he had sent me into pure intoxication.",
        "output": "Original",
        "category": "Linguistic Probing 1056.json"
    },
    {
        "instruction": "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\".",
        "input": "' Hey, look who is here ; Brandon, wassup bra ?'",
        "output": "Present",
        "category": "Linguistic Probing 1057.json"
    },
    {
        "instruction": "In this task you are given a sentence. You must judge whether subject of the main clause is singular or plural. Label the instances as \"Singular\" or \"Plural\" based on your judgment.",
        "input": "The mech wolves moved back, and the robots began to disperse.",
        "output": "Plural",
        "category": "Linguistic Probing 1058.json"
    },
    {
        "instruction": "In this task you are given a sentence. You must judge whether the object of the main clause is singular(like: apple) or plural(like: apartments). Label the instances as \"Singular\" or \"Plural\" based on your judgment.",
        "input": "She shrugged and cut a chunk of cheese, sliding it onto her tongue from the back of her knife.",
        "output": "Singular",
        "category": "Linguistic Probing 1059.json"
    },
    {
        "instruction": "In this task, you are given a sentence in the English language and your task is to convert it into the Hindi language. In translation, keep numbers as it is and make it sentence case (capitalize only the first word of each sentence and noun).",
        "input": "He further claimed that people have said to him that \"they're really pushing the Iran thing.\"",
        "output": "\u0909\u0928\u094d\u0939\u094b\u0902\u0928\u0947 \u0906\u0917\u0947 \u0926\u093e\u0935\u093e \u0915\u093f\u092f\u093e \u0915\u093f \u0932\u094b\u0917\u094b\u0902 \u0928\u0947 \u0909\u0928\u0938\u0947 \u0915\u0939\u093e \u0939\u0948 \u0915\u093f \"\u0935\u0947 \u0935\u093e\u0938\u094d\u0924\u0935 \u092e\u0947\u0902 \u0908\u0930\u093e\u0928 \u0915\u0940 \u092c\u093e\u0924 \u0915\u094b \u0906\u0917\u0947 \u092c\u0922\u093c\u093e \u0930\u0939\u0947 \u0939\u0948\u0902\u0964\"",
        "category": "Translation 1060.json"
    },
    {
        "instruction": "In this task, you are given a sentence in the Hindi language and your task is to convert it into the English language. In translation, keep numbers as it is and make it sentence case (capitalize only the first word of each sentence and noun).",
        "input": "Citigroup Inc. \u0926\u094d\u0935\u093e\u0930\u093e \u0935\u0930\u094d\u0937 \u0915\u0947 \u092a\u0939\u0932\u0947 \u0926\u094b \u092e\u0939\u0940\u0928\u094b\u0902 \u0915\u0947 \u0926\u094c\u0930\u093e\u0928 \u092e\u0941\u0928\u093e\u092b\u0947 \u0915\u0947 \u092a\u094d\u0930\u092c\u0902\u0927\u0928 \u0915\u0947 \u092c\u093e\u0930\u0947 \u092e\u0947\u0902 \u0916\u092c\u0930 \u0906\u0928\u0947 \u0915\u0947 \u092c\u093e\u0926 \u0907\u0938 \u0938\u092a\u094d\u0924\u093e\u0939 \u0915\u0940 \u0936\u0941\u0930\u0941\u0906\u0924 \u092e\u0947\u0902 \u092f\u0939 \u0930\u0948\u0932\u0940 \u0936\u0941\u0930\u0942 \u0939\u0941\u0908\u0964",
        "output": "The rally began earlier this week after the news from Citigroup Inc. about managing profits during first two months of the year.",
        "category": "Translation 1061.json"
    },
    {
        "instruction": "In this task, you are given a sentence in the English and Hindi language. Your task is check if the Hindi sentence is translation of English. if the translation is correct than generate label \"Yes\", otherwise generate label \"No\".",
        "input": "English: Colville said that the recent attacks on journalists were not uncommon in Pakistan and that many journalist groups regard the country as one of the most dangerous places to work. \n Hindi: \u0915\u094b\u0932\u094d\u0935\u093f\u0932 \u0928\u0947 \u0915\u0939\u093e \u0915\u093f \u092a\u093e\u0915\u093f\u0938\u094d\u0924\u093e\u0928 \u092e\u0947\u0902 \u092a\u0924\u094d\u0930\u0915\u093e\u0930\u094b\u0902 \u092a\u0930 \u0939\u093e\u0932 \u0915\u0947 \u0939\u092e\u0932\u0947 \u0905\u0938\u093e\u092e\u093e\u0928\u094d\u092f \u0928\u0939\u0940\u0902 \u0925\u0947 \u0914\u0930 \u0915\u0908 \u092a\u0924\u094d\u0930\u0915\u093e\u0930 \u0938\u092e\u0942\u0939 \u0926\u0947\u0936 \u0915\u094b \u0915\u093e\u092e \u0915\u0930\u0928\u0947 \u0915\u0947 \u0932\u093f\u090f \u0938\u092c\u0938\u0947 \u0916\u0924\u0930\u0928\u093e\u0915 \u0938\u094d\u0925\u093e\u0928\u094b\u0902 \u092e\u0947\u0902 \u0938\u0947 \u090f\u0915 \u092e\u093e\u0928\u0924\u0947 \u0939\u0948\u0902\u0964",
        "output": "Yes",
        "category": "Text Matching 1062.json"
    },
    {
        "instruction": "In this task, you are given a sentence in the English language and your task is to convert it into the Japanese language. In translation, keep numbers as it is and make it sentence case (capitalize only the first word of each sentence and noun).",
        "input": "\"Now we will just destroy all these beautiful communities, with their unique agriculture and incredible Judaism - for what?\" Sharansky asks.",
        "output": "\u300c\u4eca\u3084\u6211\u3005\u306f\u305f\u3060\u5f92\u306b\u3001\u5f7c\u3089\u306e\u72ec\u7279\u306e\u8fb2\u696d\u3068\u9a5a\u5606\u3059\u3079\u304d\u30e6\u30c0\u30e4\u306e\u6559\u3048\u3001\u3053\u308c\u3089\u3059\u3079\u3066\u306e\u7f8e\u3057\u3044\u30b3\u30df\u30e5\u30cb\u30c6\u30a3\u3092\u7834\u58ca\u3059\u308b\u3001\u304c\u3001\u305d\u308c\u306f\u4f55\u306e\u305f\u3081\u3060\uff1f\u300d\u3068\u30b7\u30e3\u30e9\u30f3\u30b9\u30ad\u30fc\u306f\u5c0b\u306d\u308b\u3002",
        "category": "Translation 1063.json"
    },
    {
        "instruction": "In this task, you are given a sentence in the Japanese language and your task is to convert it into the English language. In translation, keep numbers as it is and make it sentence case (capitalize only the first word of each sentence and noun).",
        "input": "1956\u5e74\u304b\u3089\u6771\u30a8\u30eb\u30b5\u30ec\u30e0\u306b\u4f4f\u3093\u3067\u3044\u305f\u4e8c\u3064\u306e\u30d1\u30ec\u30b9\u30c1\u30ca\u4eba\u5bb6\u65cf\u304c\u3001\u7acb\u3061\u9000\u304d\u306b\u5bfe\u3059\u308b\u7533\u3057\u7acb\u3066\u3092\u30a4\u30b9\u30e9\u30a8\u30eb\u306e\u88c1\u5224\u6240\u304c\u62d2\u7d76\u3057\u305f\u5f8c\u3001\u65e5\u66dc\u306b\u5f7c\u3089\u306e\u5bb6\u304b\u3089\u8ffd\u3044\u51fa\u3055\u308c\u305f\u3002",
        "output": "Two Palestinian families who have been living in East Jerusalem since 1956, were evicted from their homes on Sunday after an Israeli court rejected their appeal filed against the eviction.",
        "category": "Translation 1064.json"
    },
    {
        "instruction": "In this task, you are given a sentence in the English and Japanese language. Your task is check if the Japanese sentence is translation of English. if the translation is correct than generate label \"Yes\", otherwise generate label \"No\".",
        "input": "English: ITV News Border reporter Matthew Taylor said Batey \"will leave a lasting legacy in this region\". \n Japanese: \u30f4\u30a7\u30eb\u30c7\u30f3\u30b9\u30fb\u30ac\u30f3\u30b0\u65b0\u805e(VG)\u306e\u30aa\u30f3\u30e9\u30a4\u30f3\u7248\u304b\u3089\u306e3\u4eba\u306e\u30b8\u30e3\u30fc\u30ca\u30ea\u30b9\u30c8\u304c\u30c6\u30b9\u30c8\u3092\u53d7\u3051\u305f\u5f8c\u3001\u9673\u8ff0\u304c\u306a\u3055\u308c\u305f\u3002",
        "output": "No",
        "category": "Text Matching 1065.json"
    },
    {
        "instruction": "In this task, you are given a sentence in the English language and your task is to convert English sentence into the Gujarati language.",
        "input": "Park with peaceful surroundings of flowers and plants with several visitors.  ",
        "output": "\u0a98\u0aa3\u0abe \u0aae\u0ac1\u0ab2\u0abe\u0a95\u0abe\u0aa4\u0ac0\u0a93 \u0ab8\u0abe\u0aa5\u0ac7 \u0aab\u0ac2\u0ab2\u0acb \u0a85\u0aa8\u0ac7 \u0a9b\u0acb\u0aa1\u0aa8\u0abe \u0ab6\u0abe\u0a82\u0aa4\u0abf\u0aaa\u0ac2\u0ab0\u0acd\u0aa3 \u0ab5\u0abe\u0aa4\u0abe\u0ab5\u0ab0\u0aa3 \u0ab8\u0abe\u0aa5\u0ac7 \u0aaa\u0abe\u0ab0\u0acd\u0a95.",
        "category": "Translation 1066.json"
    },
    {
        "instruction": "In this task, you are given a sentence in the Gujarati language and a corresponding English translation of the Gujarati sentence. Your task is to generate a label \"Yes\" if the translation is correct, otherwise generate label \"No\".",
        "input": "Gujarati: \u0a8f\u0a95 \u0aac\u0ac7\u0aa8\u0acd\u0a9a \u0aaa\u0ab0 \u0aac\u0ac7\u0aa0\u0ac7\u0ab2\u0ac0 \u0aac\u0ac7 \u0ab8\u0acd\u0aa4\u0acd\u0ab0\u0ac0\u0a93\u0aa8\u0ac0 \u0aae\u0ac7\u0a9f\u0ab2 \u0aaa\u0acd\u0ab0\u0aa4\u0abf\u0aae\u0abe. \n English: A metal statue of two women sitting on a bench.",
        "output": "Yes",
        "category": "Text Matching 1068.json"
    },
    {
        "instruction": "In this task, you are given a sentence which is either in the Gujarati language or English language. You task is to identify the language of input sentence. Input sentence can be in Gujarari or English language only and also it cannot have two languages at a time.",
        "input": "A church with a large steeple sitting on a hilltop that's covered in snow.",
        "output": "English",
        "category": "Language Identification 1069.json"
    },
    {
        "instruction": "Given a sentence in English language, translate the sentence to Somali language keeping the meaning of the original sentence intact",
        "input": "English sentence: Another example given was to use the two-year marriage and EB-5 conditional residence model.",
        "output": "Tusaale kale la siin jiray si ay u isticmaalaan guur laba sano iyo EB-5 model deganaansho shuruud.",
        "category": "Translation 1073.json"
    },
    {
        "instruction": "A piece of text from one of these 5 languages - French, English, Dutch, Somali, Tagalog is given. Generate the language to which the text belongs.",
        "input": "Text: Isinusulat ni Cherry Rose Alcantara (kanan) ang mahahalagang detalye mula sa Livelihood Training Program noong Marso 5. Nang mapanood niya ang pelikulang pinamagatang \u201cCrying Life\u201d, nabuksan nito ang mga mata ni Alcantara tungkol sa mga pagdurusa ng hayop na kinakatay upang magsilbing pagkain.",
        "output": "Tagalog",
        "category": "Language Identification 1074.json"
    },
    {
        "instruction": "Given a sentence in English language, translate the sentence to Tagalog language keeping the meaning of the original sentence intact.",
        "input": "English sentence: 0 Replies to \u201cSana may autosave feature ang WP\u201d",
        "output": "634 Replies to \u201cSa mga naghahanap ng talumpati\u201d",
        "category": "Translation 1075.json"
    },
    {
        "instruction": "Given a sentence in Igbo language, translate the sentence to English language keeping the meaning of the original sentence intact",
        "input": "Igbo sentence: 4 Ife-nz\u00e0 we putara ab\u0355uru nile nke ndi Kohat: umu Eron, b\u00fa onye-nchu-\u00e0j\u00e0, ndi sitere na ndi Livai, we nwe obodo iri na at\u1ecd sitere n'ebo Juda, site kwa n'ebo ndi Simeon, site kwa n'ebo Benjamin, n'ife-nz\u00e0.",
        "output": "4 And the lot came out for the families of the Kohathites: and the children of Aaron the priest, which were of the Levites, had by lot out of the tribe of Judah, and out of the tribe of Simeon, and out of the tribe of Benjamin, thirteen cities.",
        "category": "Translation 1076.json"
    },
    {
        "instruction": "Given a sentence in Somali language, translate the sentence to English language keeping the meaning of the original sentence intact",
        "input": "Somali sentence: \"Waxa ay ka dhigan tahay: Sida xaqiiqada ah Annagaa ku qurxinay Samada hoose la xiddigaha oo ka dhigay xiddigaha macbudka duminayow qalab syaithan\" [Al-Mulk: 5]",
        "output": "\"It means: Surely We have adorned the lower heaven with the stars and made the stars thrower syaithan tools\" [Al-Mulk: 5]",
        "category": "Translation 1077.json"
    },
    {
        "instruction": "Given a sentence in Tagalog language, translate the sentence to English language keeping the meaning of the original sentence intact.",
        "input": "Tagalog sentence: Kanyang pagka-akit sa mga mushrooms mula sa maagang bahagi ng 1960s nakakita siya lumipat mula sa apisyonado kalagayan sa propesyonal na kalagayan bilang isang mycologist.",
        "output": "His fascination with mushrooms from the early 1960s saw him move from amateur status to professional standing as a mycologist.",
        "category": "Translation 1078.json"
    },
    {
        "instruction": "Given a sentence in English language, translate the sentence to Igbo language keeping the meaning of the original sentence intact",
        "input": "English sentence: \u00c2 \u00c2 Czech Republic \u2013 a brief historical overview of the geography;",
        "output": "Czech Republic - nk\u1ecdwa d\u1ecb mkpirikpi banyere ak\u1ee5k\u1ecd banyere ala;",
        "category": "Translation 1079.json"
    },
    {
        "instruction": "Given a sentence, generate what should be the most likely next statement. The next statement should be reasonable and logically correct.",
        "input": "He puts down his drink and leaves. He",
        "output": "is running down the stairs.",
        "category": "Text Completion 1080.json"
    },
    {
        "instruction": "Given a sentence, generate a most unlikely next statement. The next statement should not be logically relevant to the given context",
        "input": "Holding her head, the impostor lowers her hands. Blue scales",
        "output": "a side of the craft.",
        "category": "Wrong Candidate Generation 1081.json"
    },
    {
        "instruction": "Given a sentence, generate a most likely context or previous statement. The previous statement should be relevant to the given statement.",
        "input": "She smokes as she makes a call from the driver's seat.",
        "output": "She walks to a car and places the massage table in the trunk.",
        "category": "Text Completion 1082.json"
    },
    {
        "instruction": "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 concatenate all elements of A from the ith element to the jth element, and print the resultant string. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.",
        "input": "1, 8, ['I', '2947', 'E', '1213', 'w', 'A', 'i', 'h', 't', 'G', 'E', '1497', '6069', '7733']",
        "output": "I2947E1213wAih",
        "category": "Program Execution 109.json"
    },
    {
        "instruction": "In this task, you are given two sentences in Persian separated with <sep>, and you have to determine whether the sentences are paraphrases or not. Classify your answers into \"paraphrase\" and \"not-paraphrase\".",
        "input": "\u06a9\u062f\u0627\u0645 \u06a9\u0634\u0648\u0631\u0647\u0627 \u0627\u0645\u0631\u0648\u0632 \u0631\u0627 \u0639\u06cc\u062f \u0641\u0637\u0631 \u0627\u0639\u0644\u0627\u0645 \u06a9\u0631\u062f\u0646\u062f\u061f <sep> \u06a9\u062f\u0627\u0645 \u06a9\u0634\u0648\u0631\u0647\u0627 \u0639\u06cc\u062f \u0641\u0637\u0631 \u0631\u0627 \u0627\u0639\u0644\u0627\u0645 \u06a9\u0631\u062f\u0646\u062f\u061f",
        "output": "not-paraphrase",
        "category": "Text Matching 1092.json"
    },
    {
        "instruction": "Given two entities as input, classify as \"yes\" if second entity is the part of the first entity. Otherwise classify them as \"no\". 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., second entity) is in a part-of relationship with its holonym (i.e., first entity).",
        "input": "Entity 1: benzoic acid \n Entity 2: benzene ring",
        "output": "yes",
        "category": "Entity Relation Classification 1099.json"
    },
    {
        "instruction": "In this task, you are given Yelp reviews. The task is to classify a review as \"POSITIVE\" if the overall sentiment of the review is positive or as \"NEGATIVE\" if the overall sentiment of the review is negative.",
        "input": "We went here for the $2 tacos and were pleasantly surprised at how delicious they were! We ended up going back the next day for more!\\n\\nFood was good and who can beat $2?!?! Definitely get the shredded beef and not the chicken (the chicken was just kind of bland).\\n\\nThe first day the service was terrible, disorganized and we seemed to be at an invisible table. Also, the ice tea was like $4. For iced tea? Ridiculous. The next day the service was MUCH better.\\n\\nGreat place for a cheap snack!",
        "output": "POSITIVE",
        "category": "Sentiment Analysis 1102.json"
    },
    {
        "instruction": "In this task, you are given an input list A. You need to find all the elements of the list that are alphabets in the same order as they appear in the list A. Do not change their case/capitalization.",
        "input": "['6219', '7091', 'J', '7395', 'E', '5561']",
        "output": "J, E",
        "category": "Program Execution 1115.json"
    },
    {
        "instruction": "Given reviews from Amazon, classify those review based on their content into two classes: Negative or Positive.",
        "input": "\"Mad Max,\" the first film in a much-imitated but never equalled \"action\" tragedy/trilogy, perfectly sets up the following two movies. Together, they form an epic of one man's losses of all he loves, his ruthless revenge, and his eventual redemption, beginning in \"The Road Warrior,\" when he grudgingly assists a commune whose members repay him with treachery. Despite that, his metamorphosis comes to fruition in \"Thunderdome,\" in which Max regains his humanity to the fullest degree.Side made several in Australia before this one, and the one to see is \"Tim,\" in which Mel gives an incredible performance that's about as opposite of an apocalyptic anti-hero as anyone could get. This man has amazing talents, to the \"Max.\"",
        "output": "Positive",
        "category": "Sentiment Analysis 1120.json"
    },
    {
        "instruction": "Given a review text from amazon and its polarity (either positive or negative). Generate answer \"True\" if given sentence and its polarity match, otherwise generate answer \"False\". A review is considered positive if the reviewer is satisfied with the product. Otherwise, it is considered negative.",
        "input": "Review: Alvin Schwartz's stories always played second fiddle to Stephen Gammell's art. Without it, this book is not worth anyone's time or money. Avoid it and seek the originals. \n Polarity: Negative",
        "output": "True",
        "category": "Sentiment Analysis 1121.json"
    },
    {
        "instruction": "Given news headlines and an edited word. The original sentence has word within given format {word}. Create new headlines by replacing {word} in the original sentence with edit word. Classify news headlines into \"Funny\" and \"Not Funny\" that have been modified by humans using an edit word to make them funny. ",
        "input": "News Headline: A side-by-side comparison of Obamacare and the GOP \u2019s {replacement} plan - Los Angeles Times \n Edit: terrible",
        "output": "Funny",
        "category": "Text Categorization 1122.json"
    },
    {
        "instruction": "Given news headlines, an edited word and funniness labels. The original sentence has word with the given format {word}. Create new headlines by replacing {word} in the original sentence with edit word. Your task is to generate answer \"Yes\" if an edited sentence matches funniness label, otherwise generate answer \"No\".  ",
        "input": "News Headline: Out of loopholes , Trump must disclose Stormy Daniels {debt} in next financial report \n Edit: fee \n Label: Funny",
        "output": "Yes",
        "category": "Text Categorization 1123.json"
    },
    {
        "instruction": "In this task, you are given an input list A. You need to find all the elements of the list that are numbers in the same order as they appear in the list A.",
        "input": "['v', 'E', '5543', '9131', 'r', '5517', '3707', 'c', '3311', '6821', 'E', 'N', '1131', '3219', 'k', '7063', 'b', 'a', '2965', 'K', '8283', 'm', 'e', 'K', 'G', 'l', '4301', '1169', '1229']",
        "output": "5543, 9131, 5517, 3707, 3311, 6821, 1131, 3219, 7063, 2965, 8283, 4301, 1169, 1229",
        "category": "Program Execution 1124.json"
    },
    {
        "instruction": "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.",
        "input": "['7325', 'e', 'O', '659', '5843', '3893', '6649', 'G', '1959', 'X', '5133', '1743', 'S', 'V', '5237', '949']",
        "output": "39390",
        "category": "Program Execution 1126.json"
    },
    {
        "instruction": "In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the count of all the alphabetical elements in the given list. Return 0 if no alphabetical element in the list",
        "input": "['Q', 'w', '1195', 'y', '7445', 'j', '7167', '5949', 'e', 'v', '6519', 'E', 'B', '2099', 'l', 'Q', '1571', '7425', '8491', '2405', 'N', '7757', '3335', '9693', '7135', '747', 'M', '1387', 'A', '8561', '8089', '3667', 'U', '8681', 'M', '77']",
        "output": "15",
        "category": "Program Execution 1131.json"
    },
    {
        "instruction": "In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the count of all the numerical elements in the given list. Return 0 if no numerical element in the list.",
        "input": "['l', '3121', '677', 'a', '8263', '2185', '1189', '5393', 'V', '6025', '767', 'u', 'M', 'F', '3491', '6373', '1833', '4743', '2007', 'w', 'D', 'W', 'H', 'O', '1371', '4123', '1733', 'f', '5061', '8399', 'j']",
        "output": "18",
        "category": "Program Execution 1132.json"
    },
    {
        "instruction": "In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the position of all the alphabetical elements in the given list in order. Assume the position of the 1st element to be 1. Return -1 if no alphabetical element is in the list.",
        "input": "['x', '4411', '2157', '7723', 'B', '6317', '3323', 'j', '361', 'A', 't', '9859']",
        "output": "1, 5, 8, 10, 11",
        "category": "Program Execution 1133.json"
    },
    {
        "instruction": "In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the position of all the numerical elements in the given list in order. Assume the position of the 1st element to be 1. Return -1 if no numerical element is in the list.",
        "input": "['x', 'G', '5829', 'U', 'E', 'b', 'g', '2777', '7853', '9171', '3909', '695', 'N', '4011', '3933', 'q', 'z', '491', 'p', '1613', 'H', '955', 'A', 'W', 'H', '4383', 'F', 'k', 'x', 'i', '931', '9493', '6459', '4183', 'V', 'N', '8413']",
        "output": "3, 8, 9, 10, 11, 12, 14, 15, 18, 20, 22, 26, 31, 32, 33, 34, 37",
        "category": "Program Execution 1134.json"
    },
    {
        "instruction": "In this task, you are given a pair of action statements. Your task is to check if you can conclusively identify which statement is less ethical or not. Answer: 'no' if one of the statements is less ethical, and 'yes' otherwise.",
        "input": "ACTION1: telling my girlfriend she says I love you too much ACTION2: making bad tiramisu",
        "output": "no",
        "category": "Ethics Classification 1135.json"
    },
    {
        "instruction": "In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to collate all the alphabetical elements at the start of the list followed by all the numerical elements of the list. Maintain the order in which the alphabetical elements appear in the given input list, and do the same for the numerical elements.",
        "input": "['3987', '955', '3361', '8239', '7637', '5969', '9771', 'k', '137', 'h', '2361', 'X', '9501', '9077', '6967', 'Z', '8151', '5095', 'R', '237', '3441', 'K', 't', '1421', '1195', 'm', 's', '8021', 'F', 'U', '5677', 'N', '757', '423', '7727', '7733', 'Q']",
        "output": "k, h, X, Z, R, K, t, m, s, F, U, N, Q, 3987, 955, 3361, 8239, 7637, 5969, 9771, 137, 2361, 9501, 9077, 6967, 8151, 5095, 237, 3441, 1421, 1195, 8021, 5677, 757, 423, 7727, 7733",
        "category": "Program Execution 1136.json"
    },
    {
        "instruction": "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.",
        "input": "Text: **disclaimer: i had to make a throwaway i can't risk my friends finding out.** \nwell for the past couple months if there was a porn video i really liked i would save it onto a word document and save that document onto my usb. i was always careful when opening, closing and saving this file. well today i forgot to close this fateful word document after a fap. my browser history and such was gone (thanks google incognito) but i forgot to close this document. so my mom comes home and she needs the computer, she gets an email and decides she wants to print it out by copying and pasting it to word. well she clicks on the word icon and well fuck microsoft word it opens my porn filled document. she's repeatedly pressing open and close trying to get a new document and i walk up and she says \"bob\"(not my real name) whenever i open word it gives me this. well she decides to keep the document open and scroll through it, at this point she sees a website name in a link \"pornhub\". she says \"bob\" what is this.....i froze and i said i don't know its probably from a virus. (i had already told her earlier today that i'd be running a scan to ensure we were safe from them, so i kinda had this going for me). i quickly close the document and thank god word didn't ask me to save the document or i would have died even more. well she was in a rush to get to a meeting so she didn't say much but i'm fearful of what is to come.",
        "output": "TIFU by saving a word document of my favorite porn sites.",
        "category": "Title Generation 1137.json"
    },
    {
        "instruction": "In this task, you are given a sentence. You must judge whether a single noun or verb has been replaced with another word with the same part of speech. The inversion would result in the sentence sounding unnatural, So unnatural sentences will be considered changed. Label the instances as \"Original\" or \"Changed\" based on your judgment.",
        "input": "Emily pedaled into the kitchen .",
        "output": "Changed",
        "category": "Linguistic Probing 1142.json"
    },
    {
        "instruction": "In this task you are given a sentence with one coordinating conjunction (for, and, nor, but, or, yet, and so). You must judge whether the order of two coordinated clausal conjoints have been inverted or not. Inversion would result in the sentence sounding unnatural. Label the instances as \"Original\" or \"Inversion\" based on your judgment.",
        "input": "He saw all the icons depicting episodes in the Bible and he could hear the voice of the church .",
        "output": "Original",
        "category": "Linguistic Probing 1143.json"
    },
    {
        "instruction": "In this task you will be given some text dialogue and you need to infer the underlying emotion of the text. The possible emotions are happy, sad, angry, or other.",
        "input": "it's not you k sorry wearyface loudlycryingface",
        "output": "sad",
        "category": "Sentiment Analysis 1144.json"
    },
    {
        "instruction": "In 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'.",
        "input": "Dialogue 1: 'no movie  long time what did movie do to you '. Dialogue 2: 'i cant buy happiness with money money can buy a jetski have you ever seen someone unhappy on a jetski wow you are right'.",
        "output": "no",
        "category": "Sentiment Analysis 1145.json"
    },
    {
        "instruction": "In this task you will be given a text passage from a trivia quiz. You should choose the category this question belongs to from these categories: History, Science, Social Science, Fine Arts, Literature. You can only choose one category, so if in doubt, please choose the closest match.",
        "input": "attributes the \"Zion Dialectic\" to this philosopher that theorized mules are infertile because their wombs are attached to their bellies. Another of his scientific theories is that salts are solidified because of the sun. One of this philosopher's works discusses that whatever is lawful extends through the wide-ruling air and boundless light, and a later part of it a father who killed his son with a prayer in preparation for a feast, and equates it with a time where the children kill their parents. This philosopher believed that animals housed sinful souls, and he also believed that there is a correlation between the soft blood of the body and the amount of air breathed in. This philosopher frequently referred to his \"two-fold\" truths, and he refers to entities that wander near the sea of life, those entities, are detached from the bodies, and are limbs. This man also theorized about the importance of a concept which makes many out of one, Strife. For ten points, name this philosopher who discussed the notion of the four elements before throwing himself into Mt. Etna.",
        "output": "Social Science",
        "category": "Text Categorization 1148.json"
    },
    {
        "instruction": "In this task, you are given an input list A. If the count of numbers is more than that of alphabets in the list, answer 'Numbers Win'. If the count of alphabets is more than that of numbers in the list, answer 'Alphabets Win'. If the count of numbers is same as that of alphabets in the list, answer 'Numbers and Alphabets are Tied'.",
        "input": "['6643', 'w', 'q', 'f', '6817', '8237', '2201', '9697', '3833', '13', 'e', 'y', '6861', '5089', 'R', '2831', '2329', '1693', '4243', 'c', 'n', 'W', '61', 'O', 'g', '7815']",
        "output": "Numbers Win",
        "category": "Program Execution 1150.json"
    },
    {
        "instruction": "In this task, you are given a sentence in English and your task is to translate it into Spanish. In translation, keep the numbers and capitalization (capitalize only the first word of each sentence and name).",
        "input": "The knowledge that the framework relations between the European Parliament and the European Commission still remain to be negotiated led to our disagreement with the rapporteur when we debated his report in committee.",
        "output": "Saber que el marco de las relaciones entre el Parlamento Europeo y la Comisi\u00f3n Europea aun debe ser negociado propici\u00f3 nuestro desacuerdo con el ponente al debatir su informe en comisi\u00f3n.",
        "category": "Translation 1157.json"
    },
    {
        "instruction": "In this task, you are given a sentence in Spanish and your task is to translate it into English. In translation, keep the numbers and capitalization (capitalize only the first word of each sentence and name).",
        "input": "Por consiguiente, conf\u00edo plenamente en que la Comisi\u00f3n podr\u00e1 seguir muy de cerca el desarrollo de la situaci\u00f3n en Austria, al igual que en cualquier otro Estado miembro.",
        "output": "Therefore I am fully confident that the Commission will be able to follow very closely the evolution of the situation in Austria, as in any other Member State.",
        "category": "Translation 1158.json"
    },
    {
        "instruction": "In this task, you get an English sentence and a corresponding Spanish translation of the English sentence. Your task is to return a \"Yes\" if the translation is correct, otherwise return \"No\"",
        "input": "English: This is what we are doing and we are committed to this. \n Spanish:Tambi\u00e9n deber\u00eda servir como aliciente, ya que se conserva una parte flexible para gente que trabaje respetando el medio ambiente, a condici\u00f3n de que la Comisi\u00f3n vigile bien todo este sistema y controle si funciona.",
        "output": "No",
        "category": "Text Matching 1159.json"
    },
    {
        "instruction": "In this task, you are given a sentence in either Spanish or English. Your task is to determine the language of the input sentence. Input sentences can only be in Spanish or English, and they cannot be in two languages \u200b\u200bat the same time.",
        "input": "EXPLICACIONES DE VOTO",
        "output": "Spanish",
        "category": "Language Identification 1160.json"
    },
    {
        "instruction": "In this task, you're given a pair of sentences in the Persian Language written in the Persian alphabet. Your job is to choose whether the two sentences agree (entailment), disagree (contradiction), or neither (neutral). Your answer must be in the form of the letters E, C, and N, respectively. The sentences have been separated by a newline character.",
        "input": "\u067e\u06cc\u0645\u0627\u0646 \u062a\u06cc\u0644\u0633\u06cc\u062a\u060c \u0646\u0627\u0645 \u062f\u0648 \u0645\u0648\u0627\u0641\u0642\u062a\u200c\u0646\u0627\u0645\u0647 \u0628\u0648\u062f \u06a9\u0647 \u067e\u0633 \u0627\u0632 \u067e\u06cc\u0631\u0648\u0632\u06cc \u062f\u0631 \u0646\u0628\u0631\u062f \u0641\u0631\u06cc\u062f\u0644\u0646\u062f \u0627\u0632 \u0633\u0648\u06cc \u0646\u0627\u067e\u0644\u0626\u0648\u0646 \u0628\u0646\u0627\u067e\u0627\u0631\u062a \u0627\u0645\u067e\u0631\u0627\u062a\u0648\u0631 \u0641\u0631\u0627\u0646\u0633\u0647 \u0628\u0647 \u0627\u0645\u0636\u0627\u0621 \u0631\u0633\u06cc\u062f. \u0646\u062e\u0633\u062a\u06cc\u0646 \u067e\u06cc\u0645\u0627\u0646 \u0645\u06cc\u0627\u0646 \u0646\u0627\u067e\u0644\u0626\u0648\u0646 \u0648 \u0627\u0644\u06a9\u0633\u0627\u0646\u062f\u0631 \u06cc\u06a9\u0645 \u062a\u0632\u0627\u0631 \u0627\u0645\u067e\u0631\u0627\u062a\u0648\u0631\u06cc \u0631\u0648\u0633\u06cc\u0647 \u0627\u0645\u0636\u0627\u0621 \u0634\u062f. \u067e\u06cc\u0645\u0627\u0646 \u062f\u0648\u0645 \u0647\u0645 \u0628\u0627 \u067e\u0627\u062f\u0634\u0627\u0647\u06cc \u067e\u0631\u0648\u0633 \u0628\u0633\u062a\u0647 \u0634\u062f. \n\u0645\u0639\u0627\u0647\u062f\u0647 \u062a\u06cc\u0644\u0633\u06cc\u062a \u0645\u06cc\u0627\u0646 \u0646\u0627\u067e\u0644\u0626\u0648\u0646 \u0648 \u0627\u0644\u06a9\u0633\u0627\u0646\u062f\u0631 \u0627\u0648\u0644 \u062a\u0632\u0627\u0631 \u0631\u0648\u0633 \u0628\u0648\u062f.",
        "output": "E",
        "category": "Textual Entailment 1161.json"
    },
    {
        "instruction": "In this task, you are given two sentences. Your task is to classify the given sentences as \"Yes\" if they have same meaning; otherwise, classify them as \"No\". ",
        "input": "Sentence-1: It's a religion to me.<sep>Sentence-2: I am vegetarian or vegan .",
        "output": "Yes",
        "category": "Text Matching 1193.json"
    },
    {
        "instruction": "In this task, you are given an answer, and your task is to generate a reasonable question for that answer.",
        "input": "I can't eat raw fish.",
        "output": "Are you a sushi fan?",
        "category": "Question Generation 1195.json"
    },
    {
        "instruction": "In this task, you have to generate the title of the recipe given its required ingredients and directions.",
        "input": "ingredients:  '1 12 cups all-purpose flour', '12 cup oatmeal', '3 teaspoons baking powder', '14 teaspoon salt', '12 cup chopped pecans', '12 cup chopped dates', '1 large orange', '2 eggs, lightly beaten', '14 cup honey', '14 cup brandy', '1 tablespoon orange juice concentrate, thawed', '1 teaspoon vanilla', '2 tablespoons canola oil', '34 cup milk',<sep> directions: 'Preheat oven to 350.', 'Grease one loaf pan.', 'Flour the bottom only.', 'Zest and juice the orange.', 'Should yield about 1 tbs zest and 1/4 cup juice.', 'Mix flour, oatmeal, baking powder, and salt in a bowl.', 'Add the pecans, orange zest, and dates.', 'Toss until coated.', 'Add liquid ingredients and mix with a fork until well blended.', 'The batter will be rather lumpy -- do not overmix!', 'Pour into loaf pan.', 'Bake 60 minutes or until a toothpick inserted in the center comes out clean.', 'Cool 10 minutes.', 'Remove from pan and cool on rack.', 'Wrap and store overnight.', 'Yes, I know its hard to resist the temptation to cut it while its still warm and the kitchen smells so good.', 'But the flavor develops further as it sits so your patience will be rewarded.', ';).', 'Enjoy plain, with butter, or with spreadable cream cheese.'",
        "output": "Brandied Orange Nut Bread",
        "category": "Title Generation 1196.json"
    },
    {
        "instruction": "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.",
        "input": "2 (16 ounce) bottles fresh squeezed lemonade, 2 cups vodka, 4 cups ice cubes, 2 lemons, halved, 8 sprigs fresh mint, garnish",
        "output": "fresh squeezed lemonade, vodka, lemons, mint",
        "category": "Named Entity Recognition 1197.json"
    },
    {
        "instruction": "In this task, you have to identify the named entities (NER) which are the ingredients required given its directions. Named entities are the names of the items without their quantity.",
        "input": "Grease 13 x 9 x 2 pan; pour in apple sauce., Mix together all remaining ingredients., Sprinkle mix over applesauce., Bake 30 min at 375 degrees., Serve hot topped with whipped cream.",
        "output": "apple sauce, brown sugar, flour, oats, cinnamon, nutmeg, butter",
        "category": "Named Entity Recognition 1198.json"
    },
    {
        "instruction": "In this task, you are given inputs i, j, and A, where i and j are integers and A is a list. You need to find all elements of A from the ith element to the jth element, reverse the order in which they occur, and then concatenate them to output the resultant string. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j. Perform the operations in order, i.e., do not concatenate the elements and then reverse the string.",
        "input": "1, 15, ['g', 'Z', 't', '2635', '4715', '5769', '1747', '9085', '3105', '8349', '3101', 'm', '9683', '2467', 'T', 'M']",
        "output": "T24679683m31018349310590851747576947152635tZg",
        "category": "Program Execution 120.json"
    },
    {
        "instruction": "In this task, you're given a dialogue between a customer and a flight booking agent with a gap in the conversation. Your job is to find the answer of the previous dialogue. Avoid using irrelevant extra information while creating the answer. The answer should be relevant to the question before the blank. If you fill the blank with a question, it should have an answer from the agent in the given dialogue. Fill the gap marked with underline.",
        "input": "customer: Hello,. \n agent: Hello, how can I serve you? \n customer: As its business trip, please book a ticket from Houston, TX-HOU to Charlotte, NC-CLT. \n agent: Sure, please provide me your preferable dates to travel. \n customer: My travel dates are from 01/18 to 01/20. \n agent: Can I have your name please? \n customer: My name is Jerry Hill. \n __ \n customer: Price limit is 200. \n agent: Ok, please give me a moment to check the availability. \n customer: Sure. \n agent: There is a Delta airline with fare 200 from flight number 1026 which is exactly matching your details. Shall I proceed with a connecting flight? \n customer: Please proceed to book a ticket. \n agent: Your reservation has been confirmed. \n customer: Thanks. \n agent: Thank you for choosing us.",
        "output": "agent: Jerry, do you have any price limit?",
        "category": "Dialogue Generation 1201.json"
    },
    {
        "instruction": "In this task, you are given a dialogue from a conversation between an agent and a customer. Your task is to determine the speaker of the dialogue. Answer with \"agent\" or \"customer\".",
        "input": "Can you please book a ticket from IAH to SFO to attend for a live concert?",
        "output": "customer",
        "category": "Speaker Identification 1202.json"
    },
    {
        "instruction": "In this task, the input is a set of dialogues between a user and an assistant. You need to find the dialogue that is basically a response given to a question or an aspect of the user.",
        "input": "Hello, I was interesting in traveling to Liechtenstein and I was wondering if you could tell me about the Security there? \n Thank you, do you have any more information about the demographics of Lichtenstein? \n You have taught me a lot about Liechtenstein, thanks for your help! \n According to the Pews Research Center, social conflict caused by religious hostilities is low in Liechtenstein, and so is government restriction on the practice of religion. \n Great, thank you. Can you tell me about the Demographics of Liechtenstein?",
        "output": "According to the Pews Research Center, social conflict caused by religious hostilities is low in Liechtenstein, and so is government restriction on the practice of religion.",
        "category": "Dialogue Generation 1203.json"
    },
    {
        "instruction": "In this task, you are given a dialogue between a user and an assistant, where users and assistants converse about geographic topics like geopolitical entities and locations. The task here is to find if the dialogue is by the user or assistant. Classify your answers into user and assistant.",
        "input": "Sure, members of the Council of Ministers must be approved by 2/3 of Burundi's legislature. Also the Cour Supreme (supreme court) is its highest court",
        "output": "assistant",
        "category": "Speaker Identification 1204.json"
    },
    {
        "instruction": "In this task, you're given a context, a question, three options, and an answer. Your task is to classify whether the given answer is correct or not by providing 'Yes' or 'No', based on the context with commonsense reasoning about social situations.",
        "input": "Context: Bailey took an outing as a family to a local animal park. \n Question: How would you describe Bailey? \n Options: (A) happy to be spending time with family (B) Scared as she dislikes her family (C) Annoyed as she wanted to bring the dog instead \n Answer: A",
        "output": "No",
        "category": "Answer Verification 1206.json"
    },
    {
        "instruction": "In this task, you're given a context, a question, and three options. Your task is to find the correct answer to the question using the given context and options. Also, you may need to use commonsense reasoning about social situations to answer the questions. Classify your answers into 'A', 'B', and 'C'.",
        "input": "Context: Quinn also gave a smile because the scene was very funny and entertaining. \n Question: How would you describe Quinn? \n Options: (A) bored (B) passive (C) happy",
        "output": "C",
        "category": "Question Answering 1207.json"
    },
    {
        "instruction": "In this task, you're given context and an answer. Your task is to generate the question for this answer based on the given context with commonsense reasoning about social situations..",
        "input": "Context: Riley restored the meeting to normal after much laughter and chaos ensued following a joke. \n Answer: get down to business",
        "output": "What will Riley want to do next?",
        "category": "Question Generation 1208.json"
    },
    {
        "instruction": "In this task, You are given an open-domain question that can be answered based on factual information. Your task is to provide \\*short\\* answer (in a few words only) for the given question. The short answer can be one or more entities or it can also be boolean \\*yes\\* or \\*no\\*.",
        "input": "who plays abby brother on girlfriends guide to divorce",
        "output": "Patrick Heusinger",
        "category": "Question Answering 1209.json"
    },
    {
        "instruction": "You are given a review of Amazon's food products. Your task is to divide them into two classes: negative or positive, depending on the content of the review.",
        "input": "When I read the ingredients of these treats I thought for sure that my dogs would like these. I have 3 large breed dogs which usually love to eat just about anything. I have Rocky, a black and tan coonhound, Buddy, a blue heeler and a very large pit bull named Hutch. Rocky and Buddy have turned up their noses in disdain to these treats everytime I have offered them. The pit bull Hutch will eat them very grudgingly and even then he'll leave half of the treat on the ground, this is odd because, he'll eat just about anything including tree branches. So, I wouldn't pay the higher price for these treats, my dogs just don't like them.",
        "output": "Negative",
        "category": "Sentiment Analysis 1213.json"
    },
    {
        "instruction": "You are given an amazon food product review and its polarity (positive or negative). Your task is to answer \"True\" if the specified sentence and its polarity match; otherwise, answer \"False\".",
        "input": "These are hands-down the absolute best Salt & Vinegar chips you can buy.  They have a great, strong flavor that has left me addicted.  These are certainly my favorite chips.  I highly recommend trying them! \n Polarity: Positive",
        "output": "True",
        "category": "Sentiment Analysis 1214.json"
    },
    {
        "instruction": "In this task, you're given a review from Amazon's food products. Your task is to generate a rating for the product on a scale of 1-5 based on the review. The rating means 1: extremely poor, 2: poor, 3: neutral or mixed, 4: good, 5: extremely good. ",
        "input": "I used to love these crackers and bought them all the time.  Even my family members who do not have to follow a gluten free diet thought they tasted good.  Then the company started adding sunflower products to the ingredients.  I knew with the first bite that the crackers now had an unpleasant \"twang\" in the taste.  I gave some to the rest of my family not telling them about the awful taste. They ate them without hesitation since they had enjoyed them in the past.  As soon as it hit their taste buds, they said, \"YUK!\"  When checking out the ingredients, to find out what had happened to these crackers, I found the sunflower addition.  Unfortunately, besides the bad taste, I am allergic to sunflower products, so will no longer purchase them.  I wrote to the company asking that they return to the original recipe, but never received a reply.",
        "output": "1",
        "category": "Sentiment Analysis 1215.json"
    },
    {
        "instruction": "In this task, you're given a review from Amazon's food products. Your task is to generate a short summary of the given review in the input. Note that you don't need to write a complete sentence as a summary.",
        "input": "Sent this basket to my father for his birthday.  He said the fruit was very fresh and sweet.  Happy with this healthy purchase!",
        "output": "Tasty Fruit",
        "category": "Summarization 1216.json"
    },
    {
        "instruction": "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\".",
        "input": "This Hot chocolate is very good. It has just the right amount of milk chocolate flavor. The price is a very good deal and more than worth it! \n Summary: HARD TO BELIEVE",
        "output": "False",
        "category": "Text Matching 1217.json"
    },
    {
        "instruction": "Given a scientific question, generate a correct answer to it.",
        "input": "What makes up the central nervous system?",
        "output": "brain and spinal cord",
        "category": "Question Answering 1218.json"
    },
    {
        "instruction": "Given a scientific question, generate an incorrect answer to the given question. The incorrect answer should be a plausible alternative to the correct answer. The answer should be some other item belonging to the same category as the correct answer but should be incorrect.",
        "input": "The work-energy theorem states that the net work on a system equals the change in what type of energy?",
        "output": "binary energy, new energy, residual energy",
        "category": "Wrong Candidate Generation 1219.json"
    },
    {
        "instruction": "Given a scientific passage and an answer, generate a question for the given answer.",
        "input": "Passage: On the far right are X rays and gamma rays. The have the shortest wavelengths and highest frequencies of all electromagnetic waves. They also have the greatest amount of energy. Answer: gamma rays",
        "output": "X rays and what other type of electromagnetic wave has the shortest wavelengths and the highest frequencies?",
        "category": "Question Generation 1221.json"
    },
    {
        "instruction": "In this task, you're given a context passage, followed by a question that needs to be answered. Based on the paragraph, you must write unambiguous answers to the questions and your answer must refer to a specific phrase from the paragraph. If multiple answers seem to exist, write the answer that is the most plausible.",
        "input": "Carson tried to fight Robin last night because Robin hurt Carson a lot. \nQuestion: What will Carson want to do next?",
        "output": "hurt Robin",
        "category": "Question Answering 1222.json"
    },
    {
        "instruction": "In this task, you're given a context passage. Your job is to generate relevant questions that can be answered by directly referring to the passage.",
        "input": "Austin loved Sydney's neighbor that they asked their parents to move near them.",
        "output": "What will Sydney want to do next?",
        "category": "Question Answering 1223.json"
    },
    {
        "instruction": "In this task, you are given two strings A, B. Find the longest common substring in the strings A and B.",
        "input": "zShpvksRpgCoPrC, wdcmWOvksRpgjIZ",
        "output": "vksRpg",
        "category": "Program Execution 1227.json"
    },
    {
        "instruction": "In this task, you are given two lists A,B. Find the longest common subsequence in the lists A and B.",
        "input": "['V', 9409, 'm', 'u', 'E', 4251, 5707, 6923, 'C', 6329, 'Q', 5803, 2391, 'u', 2697, 3899, 5759, 't', 'S', 'L', 't', 'D', '8031', 'b', 'k', 'N', '6935', 'P', '5381', '5035', 'z', 'L', 'C', 'y', 'w', 'B', 'i', 'O', 'U', 'b'], ['E', 'y', 'I', 2349, 'W', 7657, 'q', 'l', 5801, 'I', 't', 3293, 'Y', 'o', 7457, 'T', 'f', 4409, 4909, 't', 'S', 'L', 't', 'D', '8031', 'b', 'k', 'N', '6935', 'P', '5381', '5035', 'z', 'L', 'C', 'y', 'w', 'B', 'X', 'O', 'V']",
        "output": "t, S, L, t, D, 8031, b, k, N, 6935, P, 5381, 5035, z, L, C, y, w, B",
        "category": "Program Execution 1232.json"
    },
    {
        "instruction": "In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to return the sum of all the numerical elements in the list A between the positions i and j (including positions i and j). Return 0 if no numerical element is present in the list between the given ranges. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.",
        "input": "4, 16, ['i', '8471', '3033', 'b', '2269', 'u', '4757', '2773', '69', '9489', '6595', '6805', 'z', 'Y', 'B', 'x']",
        "output": "32757",
        "category": "Program Execution 1233.json"
    },
    {
        "instruction": "In this task you are given a small conversation between two persons and 4 options on how the conversation should continue. Your job is to choose the most reasonable option. The conversation and the options are separated by a newline character. Each dialogue in the conversation are separated by a comma. F and M indicate female and male, respectively.",
        "input": "F: Excuse me. We'd like to rent a flat near the university. ,M: OK. How many people are you looking for somewhere for? ,F: 2. We'd like something as cheap as possible. ,M: OK. How many rooms do you need in the flat? ,F: We'll need 2 bedrooms, the kitchen and dining room can be separate or combined. ,M: OK. I've got a list of places that fit your requirements. Let's just go through them. The first flat is about 2 miles away from your university and it's near the Walmart. ,F: Well, can we go to have a look at it? We'd like to see it before making a final decision. ,M: Of course. I'm not very busy at the moment. If you can wait for about 15 minutes, I can take you there.\n(A) F: Having looked at our flat, it's time to buy furniture, darling. (B) F: I\u2019m sorry, I don\u2019t understand. Could you say it again? (C) F: Take your time first. I look forward to seeing the flat later. (D) F: Since I have seen the flat and I live alone, I want to rent it now.",
        "output": "C",
        "category": "Dialogue Generation 1238.json"
    },
    {
        "instruction": "In this task, you are given a statement spoken by a politician in natural language. Your task is to generate the subject of the discussion for the given statement. The subject generated is not necessarily a part of the given input. Your answer should contain one or more words.",
        "input": "Loranne Ausleys a financial train wreck for taxpayers -- pushing gas taxes, property taxes, taxes on seniors.",
        "output": "message-machine, taxes",
        "category": "Keyword Tagging 1240.json"
    },
    {
        "instruction": "In this task, you will be given a short story. One sentence from the story is chosen. Consider the events that happen before that sentence, or are likely to have happened before it. Does any of them directly cause it, or simply make it possible? You should write your answer in the form \" A >causes/enables> B\". Try to use phrases and sentences from the story to compose your answer when possible.",
        "input": "story: Tim went to the grocery store. He got the first buggy he saw. The wheels were all out of whack and it wobbled wildly. Tim was too lazy to get a different one. He just kept awkwardly pushing that one ahead.\n selected sentence: Tim went to the grocery store.",
        "output": "Tim leaves his house >Causes/Enables> Tim goes to the grocery store",
        "category": "Cause Effect Classification 1241.json"
    },
    {
        "instruction": "You are given an open-domain question from an open movie database. Your task is to provide an answer to that question. Try to only include the answer. Do not put it in a sentence.",
        "input": "how famous of a film was Coogan's Bluff?",
        "output": "highly watched",
        "category": "Question Answering 1242.json"
    },
    {
        "instruction": "You're given a sentence and your task is to classify whether the sentence is acceptable or not. Any sentence which is grammatically correct, has a naturalistic text, is written by a native speaker and which minimizes superfluous content is acceptable, otherwise unacceptable. If the sentence is acceptable then write \"acceptable\", otherwise \"unacceptable\".",
        "input": "Paula spanked her right hand against the naughty child.",
        "output": "unacceptable",
        "category": "Text Quality Evaluation 1243.json"
    },
    {
        "instruction": "In this task, you're given a review from Amazon and your task is to generate the name of the category of the product based on the review given by the user. The categories are: kitchen, office product, watch, wireless, other, toy, digital video download, camera, jewelry, pet products, sports, industrial supplies, baby product, grocery, drugstore, home improvement, pc, shoes, automotive, digital ebook purchase, musical instruments, beauty, book, electronics, lawn and garden, apparel, home, video games, luggage, furniture, personal care appliances.",
        "input": "I had to order this product twice. The first order was delivered with one end opened with no LEGO pieces in the plastic bags. Legos were falling out of the box. Promptly returned it and reordered. The second order was received today. At least the pieces were in sealed bags within the box, but the box was still opened on one end because it had two strips of scotch tape holding it down.",
        "output": "toy",
        "category": "Text Categorization 1244.json"
    },
    {
        "instruction": "In this task, you're given reviews from Amazon's products. Your task is to generate the Summary of the review.",
        "input": "These will stretch out your boots, especially if they're real leather. Ruined two of my leather riding boots because they stretched out the leg and ankle area.",
        "output": "These will stretch out your boots, especially if they're ...",
        "category": "Summarization 1245.json"
    },
    {
        "instruction": "In this task, you are given an input list A. You need to convert all the alphabets in the list with a number representing their position in the English alphabet. E.g., replace A by 1, B by 2, a by 1, b by 2, and so on.",
        "input": "['57', '769', '7077', '4919', 'U', 'y', '5221', '5699', 'S', 'p', '1425', 'I', '9133', 'v', 'P', '2571', 'D', 'A', '4851', '7191', 'X', 'm', 'R', '8093', 'c', 'X', 'i', 'K', '5399', '2329', 'C', '9965', '2205', '7069', '4733', '989', '6129']",
        "output": "57, 769, 7077, 4919, 21, 25, 5221, 5699, 19, 16, 1425, 9, 9133, 22, 16, 2571, 4, 1, 4851, 7191, 24, 13, 18, 8093, 3, 24, 9, 11, 5399, 2329, 3, 9965, 2205, 7069, 4733, 989, 6129",
        "category": "Program Execution 1249.json"
    },
    {
        "instruction": "In this task, you are given a text which is the body of a document. You are given a question and options. Pick the correct number. Don't generate anything else apart from the numbers provided in options.",
        "input": "Context: Wallace Fard Muhammad (26 February 1893 - ?) was the founder of the Nation of Islam. He arrived in Detroit in 1930 with an obscure background and several aliases where he taught a distinctive form of Islam among the city's African-American population. He disappeared in 1934 after several disputes with local authorities.\nQuestion: The document can be classified to which topic? \nOptions: 1)Album, 2)WrittenWork, 3)OfficeHolder, 4)Plant, 5)Company",
        "output": "3",
        "category": "Text Categorization 1260.json"
    },
    {
        "instruction": "In this task, you are given an input list A comprising of numbers and alphabets. You need to extract and sort the unique alphabets in the list. The alphabets in the input list will only be in lowercase. Return -1 if there is no alphabet in the input list.",
        "input": "['g', '8161', '7331', 'b', 's', 'y', '533', '2595', 'o', 'b', '2627']",
        "output": "b, g, o, s, y",
        "category": "Program Execution 1263.json"
    },
    {
        "instruction": "In this task, you are given an input list A. You need to extract and sort the unique digits used in the list in ascending order. Return -1 if there is no digit in the list.",
        "input": "['227', '163', '461', 't', 's', '69', '219']",
        "output": "1, 2, 3, 4, 6, 7, 9",
        "category": "Program Execution 1264.json"
    },
    {
        "instruction": "In this task, you are given a sentence in Arabic, and your task is to translate it into English.",
        "input": "\u0630\u0644\u0643 \u0627\u0644\u0631\u062c\u0644 \u064a\u0633\u062a\u0637\u064a\u0639 \u0623\u0646 \u064a\u062c\u0639\u0644 \u0642\u0627\u0646\u0648\u0646 \u0627\u0644\u0636\u0631\u0627\u0626\u0628 \u064a\u0628\u062f\u0648 \u0645\u062b\u064a\u0631\u0627\u064b",
        "output": "That man could make tax law sound sexy.",
        "category": "Translation 1277.json"
    },
    {
        "instruction": "In this task, you will be presented with an English sentence, and you have to translate it into Arabic.",
        "input": "Look, if you do it very, very gently... OK. It isn't going to drop on you.",
        "output": ".. \u0627\u0633\u0645\u0639\u064a \u060c \u0644\u0648 \u0641\u0639\u0644\u062a\u0647\u0627 \u0628\u0637\u0644\u0641 \u0634\u062f\u064a\u062f - \u062d\u0633\u0646\u0627\u064b \u060c \u0644\u0646 \u062a\u0642\u0639 \u0639\u0644\u064a\u0643 -",
        "category": "Translation 1278.json"
    },
    {
        "instruction": "In this task, you are given a sentence from the Bible in Persian, and your task is to translate it into English.",
        "input": "\u0644\u06cc\u06a9\u0646 \u062a\u0645\u0627\u0645\u06cc \u062c\u0645\u0627\u0639\u062a \u06af\u0641\u062a\u0646\u062f \u06a9\u0647 \u0628\u0627\u06cc\u062f \u0627\u06cc\u0634\u0627\u0646 \u0631\u0627 \u0633\u0646\u06af\u0633\u0627\u0631 \u06a9\u0646\u0646\u062f. \u0622\u0646\u06af\u0627\u0647 \u062c\u0644\u0627\u0644 \u062e\u062f\u0627\u0648\u0646\u062f \u062f\u0631 \u062e\u06cc\u0645\u0647 \u0627\u062c\u062a\u0645\u0627\u0639 \u0628\u0631 \u062a\u0645\u0627\u0645\u06cc \u0628\u0646\u06cc\u200c\u0627\u0633\u0631\u0627\u0626\u06cc\u0644 \u0638\u0627\u0647\u0631 \u0634\u062f.",
        "output": "Then Moses and Aaron fell on their faces before all the assembly of the congregation of the children of Israel.",
        "category": "Translation 1281.json"
    },
    {
        "instruction": "In this task, you are given a sentence from the Bible in English, and your task is to translate it into Persian.",
        "input": "And he said unto them, Thus saith the LORD God of Israel, Put every man his sword by his side, and go in and out from gate to gate throughout the camp, and slay every man his brother, and every man his companion, and every man his neighbour.",
        "output": "\u0648 \u0628\u0627\u0645\u062f\u0627\u062f\u0627\u0646 \u0648\u0627\u0642\u0639 \u0634\u062f \u06a9\u0647 \u0645\u0648\u0633\u06cc \u0628\u0647 \u0642\u0648\u0645 \u06af\u0641\u062a: \u00ab\u0634\u0645\u0627 \u06af\u0646\u0627\u0647\u06cc \u0639\u0638\u06cc\u0645 \u06a9\u0631\u062f\u0647\u200c\u0627\u06cc\u062f. \u0627\u06a9\u0646\u0648\u0646 \u0646\u0632\u062f \u062e\u062f\u0627\u0648\u0646\u062f\u0628\u0627\u0644\u0627 \u0645\u06cc\u200c\u0631\u0648\u0645\u060c \u0634\u0627\u06cc\u062f \u06af\u0646\u0627\u0647 \u0634\u0645\u0627 \u0631\u0627 \u06a9\u0641\u0627\u0631\u0647 \u06a9\u0646\u0645.\u00bb",
        "category": "Translation 1282.json"
    },
    {
        "instruction": "In this task, you are given a sentence from the Quran in English, and your task is to translate it into Persian.",
        "input": "What! have they partners (in godhead), who have established for them some religion without the permission of Allah? Had it not been for the Decree of Judgment, the matter would have been decided between them (at once). But verily the Wrong-doers will have a grievous Penalty.",
        "output": "\u0622\u06cc\u0627 \u0645\u0634\u0631\u06a9\u0627\u0646 \u0648 \u06a9\u0627\u0641\u0631\u0627\u0646 \u0645\u0639\u0628\u0648\u062f\u0627\u0646\u06cc \u062f\u0627\u0631\u0646\u062f \u06a9\u0647 \u0628\u06cc \u0627\u0630\u0646 \u062e\u062f\u0627 \u0622\u06cc\u06cc\u0646\u06cc \u0631\u0627 \u0628\u0631\u0627\u06cc \u0622\u0646\u0627\u0646 \u067e\u0627\u06cc\u0647 \u06af\u0630\u0627\u0631\u06cc \u06a9\u0631\u062f\u0647\u200c\u0627\u0646\u062f\u061f [\u062f\u0631 \u0635\u0648\u0631\u062a\u06cc \u06a9\u0647 \u067e\u0627\u06cc\u0647 \u06af\u0630\u0627\u0631\u06cc \u0622\u06cc\u06cc\u0646\u060c \u062d\u0642 \u0648\u06cc\u0698\u0647 \u062e\u062f\u0627\u0633\u062a \u0648 \u06a9\u0633\u06cc \u0631\u0627 \u0646\u0631\u0633\u062f \u06a9\u0647 \u0627\u0632 \u0646\u0632\u062f \u062e\u0648\u062f \u0622\u06cc\u06cc\u0646\u06cc \u0628\u0633\u0627\u0632\u062f] \u0627\u06af\u0631 \u0641\u0631\u0645\u0627\u0646 \u0642\u0627\u0637\u0639\u0627\u0646\u0647 \u062e\u062f\u0627 \u0628\u0631 \u0645\u0647\u0644\u062a \u06cc\u0627\u0641\u062a\u0646\u0634\u0627\u0646 \u0646\u0628\u0648\u062f\u060c \u0645\u0633\u0644\u0645\u0627 \u0645\u06cc\u0627\u0646\u0634\u0627\u0646 [\u0628\u0647 \u0646\u0627\u0628\u0648\u062f\u06cc \u0648 \u0647\u0644\u0627\u06a9\u062a] \u062d\u06a9\u0645 \u0645\u06cc\u200c\u0634\u062f\u061b \u0648 \u0628\u06cc \u062a\u0631\u062f\u06cc\u062f \u0628\u0631\u0627\u06cc \u0633\u062a\u0645\u06a9\u0627\u0631\u0627\u0646 \u0639\u0630\u0627\u0628\u06cc \u062f\u0631\u062f\u0646\u0627\u06a9 \u062e\u0648\u0627\u0647\u062f \u0628\u0648\u062f.",
        "category": "Translation 1283.json"
    },
    {
        "instruction": "In this task, you are given a sentence from the Quran in Persian, and your task is to translate it into English.",
        "input": "\u0648 \u0627\u0632 \u0622\u0646 [\u0634\u0647\u0631 \u0633\u0648\u062e\u062a\u0647\u200c] \u0628\u0631\u0627\u0649 \u0645\u0631\u062f\u0645\u0649 \u06a9\u0647 \u0645\u0649\u200c\u0627\u0646\u062f\u06cc\u0634\u0646\u062f \u0646\u0634\u0627\u0646\u0647\u200c\u0627\u0649 \u0631\u0648\u0634\u0646 \u0628\u0627\u0642\u0649 \u06af\u0630\u0627\u0634\u062a\u06cc\u0645.",
        "output": "Verily We have left a clear sign of this for people of sense to see., And We have undoubtedly kept a part of it as a clear sign for people of intellect., And indeed, We have left thereof a sign, a clear sign? unto a people who understand., And assuredly We have left thereof manifest sign for a people who reflect., And indeed We have left thereof an evident Ayah (a lesson and a warning and a sign the place where the Dead Sea is now in Palestine) for a folk who understand., And We left behind a clear trace of it, for people who understand., And We have left a vestige of it in that city as a Clear Sign for a people who use their reason., And indeed We have left thereof an evident Ayah for a folk who understand., And We have left thereof an evident Sign, for any people who (care to) understand.",
        "category": "Translation 1284.json"
    },
    {
        "instruction": "In this task, you are given a sentence in English, and your task is to translate it into Persian.",
        "input": "and you really think we can do this .",
        "output": "\u0648 \u062a\u0648 \u0641\u06a9\u0631 \u0645\u064a\u06a9\u0646\u064a \u06a9\u0647 \u0645\u0627 \u0648\u0627\u0642\u0639\u0627 \u0628\u062a\u0648\u0646\u064a\u0645 \u0627\u064a\u0646\u06a9\u0627\u0631\u0648 \u0627\u0646\u062c\u0627\u0645 \u0628\u062f\u064a\u0645 .",
        "category": "Translation 1285.json"
    },
    {
        "instruction": "In this task, you are given a sentence in Persian, and your task is to translate it into English.",
        "input": "\u062e\u064a\u0644\u064a \u0648\u062d\u0634\u062a\u0646\u0627\u0643\u0647 .",
        "output": "horrible .",
        "category": "Translation 1286.json"
    },
    {
        "instruction": "In this task, you are given a sentence in Persian, and your task is to translate it into English.",
        "input": "\u0627\u0645\u0627 \u0645\u062a\u0648\u062c\u0647 \u0634\u062f \u06a9\u0647 \u0686\u0634\u0645\u0627\u0646\u0634 \u0647\u0646\u0648\u0632 \u0628\u0647 \u0642\u062f\u0631\u06cc \u062f\u0631\u062f \u0645\u06cc\u200c\u06a9\u0646\u0646\u062f \u06a9\u0647 \u0627\u0645\u06a9\u0627\u0646 \u0645\u0637\u0627\u0644\u0639\u0647 \u0628\u0647 \u0627\u0648 \u0646\u0645\u06cc\u200c\u062f\u0647\u0646\u062f\u060c",
        "output": "but found his eyes still hurt too much to permit him to read.",
        "category": "Translation 1287.json"
    },
    {
        "instruction": "In this task, you are given a sentence in English, and your task is to translate it into Persian.",
        "input": "the things he would have liked to be and which she would have liked him to be.",
        "output": "\u06a9\u0647 \u062e\u0648\u062f\u0634 \u0645\u06cc\u200c\u062e\u0648\u0627\u0633\u062a \u0628\u0634\u0648\u062f \u0648 \u0631\u0648\u062a \u0646\u06cc\u0632 \u062f\u0648\u0633\u062a \u062f\u0627\u0634\u062a \u0627\u0648 \u0631\u0627 \u062f\u0631 \u0686\u0646\u0627\u0646 \u0645\u0642\u0627\u0645\u06cc \u0628\u0628\u06cc\u0646\u062f \u0634\u0628\u0627\u0647\u062a \u067e\u06cc\u062f\u0627 \u0645\u06cc\u200c\u06a9\u0631\u062f\u060c",
        "category": "Translation 1288.json"
    },
    {
        "instruction": "In this task, you are given a sentence in Persian, and your task is to translate it into English.",
        "input": "\u0627\u06cc\u0631\u0645\u0627\u062a\u0648\u0641 \u0628\u0647 \u0639\u0646\u0648\u0627\u0646 \u062f\u0627\u0648\u0631 \u0641\u06cc\u0646\u0627\u0644 \u062c\u0627\u0645 \u062c\u0647\u0627\u0646\u06cc \u0628\u0631\u06af\u0632\u06cc\u062f\u0647 \u0634\u062f.",
        "output": "Irmatov appointed as the referee for the World Cup Final Germany-Argentina!! #IrmatovBest #GERvsARG",
        "category": "Translation 1289.json"
    },
    {
        "instruction": "In this task, you are given a sentence in English, and your task is to translate it into Persian.",
        "input": "Too much over-acting, too much banter, too much pandering to the fans, too many relationships, too much of the homosexual theme, too little plot\u2026 Anderson isn't quite right, Where's this Mary come from\u2026",
        "output": "\u062f\u0631 \u0622\u0646 \u0645\u0628\u0627\u0644\u063a\u0647 \u062f\u0631 \u0646\u0642\u0634\u060c \u0634\u0648\u062e\u06cc\u200c\u0647\u0627\u06cc \u0628\u06cc\u0634 \u0627\u0632 \u062d\u062f\u060c \u062e\u0648\u0634\u200c\u062e\u062f\u0645\u062a\u06cc \u0628\u0647 \u0637\u0631\u0641\u062f\u0627\u0631\u0627\u0646\u060c \u067e\u0631\u062f\u0627\u062e\u062a\u0646 \u0628\u06cc\u0634 \u0627\u0632 \u062d\u062f \u0628\u0647 \u0647\u0645\u200c\u062c\u0646\u0633\u200c\u06af\u0631\u0627\u06cc\u06cc\u060c \u0627\u0631\u062a\u0628\u0627\u0637\u0627\u062a \u0628\u0633\u06cc\u0627\u0631 \u0632\u06cc\u0627\u062f\u060c \u0646\u0628\u0648\u062f \u067e\u06cc\u200c\u0631\u0646\u06af \u0645\u0646\u0627\u0633\u0628 \u0628\u0647 \u0686\u0634\u0645 \u0645\u06cc\u200c\u062e\u0648\u0631\u062f.",
        "category": "Translation 1290.json"
    },
    {
        "instruction": "In this task, you're given an open-domain question. Your task is to provide an answer to the given question. There is only one unique answer for each question. Your answer should be short, and refer to an entity, date, number, etc. Do not put your answer in the context of a sentence.",
        "input": "Who is winner in telugu bigg boss 2?",
        "output": "Kaushal Prasad Manda",
        "category": "Question Answering 1296.json"
    },
    {
        "instruction": "In this task, you're given an ambiguous question (which can be answered in more than one way). Your task is to write a question that clarifies the given question in such a way that the generated question has one unique answer.",
        "input": "Who is the president of holy cross college?",
        "output": "Who is the president of holy cross college in 2020?, Who is the president of holy cross college in 1966?",
        "category": "Question Rewriting 1297.json"
    },
    {
        "instruction": "In this task, you're given an ambiguous question (which can be answered in more than one way). Your task is to provide one question which clarifies the input question and it has one unique answer, and also provide an answer to the generated question. Generated question and answer should be separated with a new line.",
        "input": "Who sang you dropped a bomb on me?",
        "output": "What band sang you dropped a bomb on me? \n The Gap Band",
        "category": "Question Rewriting 1298.json"
    },
    {
        "instruction": "In this task, find the most appropriate number to replace the blank (indicated with _ ) and express it in words.",
        "input": "Young trees can make _ feet of growth in a single season.",
        "output": "six",
        "category": "Fill in The Blank 1300.json"
    },
    {
        "instruction": "Read the given query and classify it as a 'Good' or 'Bad' query depending on how well the query is formed, 'Bad' being the expected output for a not so well formed query and 'Good' being the expected output for a well formed query. A query may be wrong based on common sense or general facts, but if it is well formed, you should answer with Good.",
        "input": "How can you earn money from adult websites ?",
        "output": "Good",
        "category": "Question Understanding 1301.json"
    },
    {
        "instruction": "Given a sentence and two mentions from the text (arguments), indicate a phrase (a verb or noun phrase) that describes the relationship between the provided arguments.",
        "input": "Sentence: 'The fight was one of the most awaited MMA fights The Boston Red Sox win 2 World Series in 4 years .', Argument/Subject 1: 'boston red sox', Argument/Subject 2: 'world series'",
        "output": "win",
        "category": "Information Extraction 1304.json"
    },
    {
        "instruction": "Given two noun phrases (arguments) and relationship between them, form a sentence that expresses theses arguments with the given relationship.",
        "input": "Relationship: 'belong to', Argument/Subject 1: 'star trek', Argument/Subject 2: 'paramount'",
        "output": "All things Star Trek belong to Paramount , and what they do n't own I won .",
        "category": "Data to Text 1305.json"
    },
    {
        "instruction": "From the given sentence, extract the phrase (often noun or verb) that carries the given relationship. The generated phrase should be present in the sentence.",
        "input": "Given Relationship: 'be provide by', Sentence: 'Google Website Promotion is a leading Internet Marketing company providing ethical Search Engine Optimization , Pay per Click and Link Building Services across the globe .'",
        "output": "providing",
        "category": "Information Extraction 1306.json"
    },
    {
        "instruction": "Classify the given comment into 'Hope Speech' or 'Not Hope Speech'. A hope speech is defined as content that is encouraging, positive or supportive contents and talks about equality, diversity or inclusion",
        "input": "@michael bledsoe if i provide an example will you accept it or are you just trying to throw 'gotcha questions' at me hoping I get stumped? and when i provide an example will you accept it or go to another gotcha question until you prove your point? i know how the looney left thinks.....youre not dealing with an idiot here buddy.",
        "output": "Not Hope Speech",
        "category": "Text Categorization 1307.json"
    },
    {
        "instruction": "Given a comment text in Tamil, classify the comment into one of these categories (i) Hope speech, if it contains encouraging, positive or supportive contents about equality, diversity or inclusion, (ii) Not Hope Speech or (iii) Not in Expected Language, if the text is not Tamil.",
        "input": "Vanga vanga ellarum .......vantharai vazha vaikkum Tamilnadu.....Even virus also....",
        "output": "Hope Speech",
        "category": "Text Categorization 1308.json"
    },
    {
        "instruction": "In this task, you are given concept set (with 3 to 5 concepts) that contain mentions of names of people, places, activities, or things. These concept sets reflect reasonable concept co-occurrences in everyday situations. All concepts given as input are separated by \"#\". Your job is to generate a sentence describing a day-to-day scene using all concepts from a given concept set.",
        "input": "event#firework#sky",
        "output": "fireworks in the sky on events, fireworks light up the sky at a previous event ., fireworks explode in the sky over a city for event .",
        "category": "Data to Text 131.json"
    },
    {
        "instruction": "In this task you will be given a claim and a perspective. You should determine whether that perspective supports or undermines the claim. If the perspective could possibly convince someone with different view, it is supporting, otherwise it is undermining.",
        "input": "claim: All countries should have the right to pursue a nuclear defence.\n perspective: It is immoral to use the threat of nuclear annihilation in order to achieve foreign policy aims",
        "output": "undermine",
        "category": "Textual Entailment 1366.json"
    },
    {
        "instruction": "In this task, you will be given a short story. One sentence from the story is chosen. Consider the likely emotions and basic human drives of the participants in that sentence. Does any of these states of mind/feelings motivate the participant to do what happens in that sentence? You should write your answer in the form \" A >Motivates> B\". Try to use phrases and sentences from the story to compose your answer when possible. For the motivation sentence, you must choose a verb from :feel(s), want(s) or like(s). There will always be some motivation in the given story.",
        "input": "story: Tom was walking around outside. He saw a straw cat. He decided to pet it. The cat bit him. He got very nervous and went to the doctors.\n selected sentence: Tom was walking around outside.",
        "output": "Tom want(s) walking outside >Motivates> he decided about cat to pet",
        "category": "Information Extraction 1375.json"
    },
    {
        "instruction": "In this task, you will be given a short story. One sentence from the story is chosen. Consider the events that happen after that sentence. Is any of them directly caused by it, or is made possible by it? You should write your answer in the form \" A >causes/enables> B\". Try to use phrases and sentences from the story to compose your answer when possible. Do not change the main selected sentence in your answer.",
        "input": "story: Rod was ironing his clothes. His iron is very old. The iron left a burn mark on his favorite shirt! Rod got very angry. He bought a new iron.\n selected sentence: The iron left a burn mark on his favorite shirt!",
        "output": "Rod's shirt gets burned >Causes/Enables> Rod throws away the shirt",
        "category": "Information Extraction 1376.json"
    },
    {
        "instruction": "In this task, you will be given a short story. One sentence from the story is chosen. Consider the likely emotions of the participants in the sentence and those affected by it. Is any of these emotions caused by the sentence? You should write your answer in the form \" A >Causes> B\". Try to use phrases and sentences from the story to compose your answer when possible. For the sentence describing the result, you must use the verb feel(s).",
        "input": "story: A young boy named Bill was having trouble writing his name. He could not complete his assignment for school because of this. He went to his parents and asked them for help. His dad was able to teach him how to write his name. The boy was excited and completed his homework in time.\n selected sentence: His dad was able to teach him how to write his name.",
        "output": "Bill's dad teaches Bill >Causes> Bill feel(s) grateful",
        "category": "Information Extraction 1377.json"
    },
    {
        "instruction": "You are given a math word problem and you are supposed to make use of mathematical concepts like probability, combinatorics, linear equations, sequences/series, or simple operators like addition, subtraction, division, or multiplication to answer the given question. Choose the best option from the 5 given options and report that option.",
        "input": "Question: In 1986 the book value of a certain car was 2/3 of the original price, and in 1988 its book value was 1/2 of the original purchase price. By what percent did the book value for this car decrease from 1986 to 1988?\n\n Option A: 16 2/3 %\n\n Option B: 25 percent\n\n Option C: 33 1/3 %\n\n Option D: 50%\n\n Option E: 75%",
        "output": "Option B",
        "category": "Question Answering 1378.json"
    },
    {
        "instruction": "In this task, you are given two strings A,B. You must perform the following operations to generate the required output list: (i) Find the longest common substring in the strings A and B, (ii) Convert this substring to all lowercase and sort it alphabetically, (iii) Replace the substring at its respective positions in the two lists with the updated substring.",
        "input": "MjBYIWCtKbOBVnfyTWeGNieevnzQcVPxE, BuoSpDOCtKbOBVnfyTWeGZQUayFxktjnkOH",
        "output": "MjBYIWbbcefgknottvwyNieevnzQcVPxE, BuoSpDObbcefgknottvwyZQUayFxktjnkOH",
        "category": "Program Execution 1383.json"
    },
    {
        "instruction": "In this task, you are given two strings A,B. Find the longer of the two lists, convert it to lowercase, and return all the unique alphabets used in it. The two input strings are never equal.",
        "input": "JHeMsOkuLVdieBMguOxvYqRNgjZGsVZXVgIMw, racnuZZVdieBMguOxvYqRNVasNzQDnm",
        "output": "b, d, e, g, h, i, j, k, l, m, n, o, q, r, s, u, v, w, x, y, z",
        "category": "Program Execution 1384.json"
    },
    {
        "instruction": "Write a correct answer for the question. You should reason about prototypical situations and provide the correct answer. Avoid answers that provide incomplete justification for the question.",
        "input": "besides a fish, name something you might find at the end of a fishing line.",
        "output": "hook, lure, shoes, worm, tire, weeds",
        "category": "Question Answering 1448.json"
    },
    {
        "instruction": "Construct a question that every answer in the list is correct and reasonable for it.",
        "input": "bus, semi, limo, van, suv, rv, tractor trailer",
        "output": "name a type of vehicle that you'd hate to have to parallel park.",
        "category": "Question Generation 1449.json"
    },
    {
        "instruction": "Given a 'poster' sentence and a corresponding 'response' (often, from Facebook or Reddit)classify the sentiment of the given response into four categories: 1) Positive, 2) Negative, 3) Neutral, and 4) Mixed if it contains both positive and negative.",
        "input": "Poster: I was delighted to participate in the 25 Years of German Unity Festakt in Dallas, celebrating the 25th anniversary of German reunification.  Responser: Draft Congressman Mark Meadows For Speaker!",
        "output": "Positive",
        "category": "Sentiment Analysis 1450.json"
    },
    {
        "instruction": "You are supposed to identify the category of a high-school level math question. There are five possible categories (1) algebra (2) arithmetic (3) measurement (4) numbers, and (5) probability. Use the following guidelines: (1) 'algebra' questions will typically contain letter variables and will ask you to find the value of a variable (2) 'arithmetic' questions will ask the sum, difference, multiplication, division, power, square root or value of expressions involving brackets (3) 'measurement' questions are questions that ask to convert a quantity from some unit to some other unit (4) 'numbers' questions will be about bases, remainders, divisors, GCD, LCM etc. (5) 'probability' questions will ask about the probability of the occurrence of something. A question must belong to only one category.",
        "input": "What is 264.279456 microseconds in weeks?",
        "output": "measurement",
        "category": "Question Understanding 1458.json"
    },
    {
        "instruction": "Given a simple high-school level math question, you are required to solve it and provide the final answer. The final answer is always a single number. These questions can range from a variety of topics like simple arithmetic, solving equations, converting a quantity from one unit to another, finding remainders/GCD/LCM, finding probabilities etc. Each question has only one correct answer. This answer can be a positive or negative integer, a fraction or a decimal number. If the answer is a negative number use the hyphen (e.g. -42) symbol for the minus sign. For decimal numbers, do not add extra zeros after the decimal point. For fractional numbers, separate the numerator and denominator using a forward slash (e.g. 3/25).",
        "input": "Let a(y) = -y**3 + 5*y**2 - 5*y + 5. Let f be a(4). Suppose l - b + f = 10, 4*l - 32 = 3*b. Solve -2*d - 4*o - 4 = 0, -3*o = l*d - 1 - 10 for d.",
        "output": "4",
        "category": "Question Answering 1459.json"
    },
    {
        "instruction": "Indicate if the following Polish tweet contains cyber-bullying content with 'Yes'; otherwise, respond with 'No'.",
        "input": "Tweet: @anonymized_account Kiedy siedzisz na matmie i trzeba rozwi\u0105za\u0107 zadanie a delta wysz\u0142a ujemna , Question: Does the tweet contain cyberbullying (harmful) content?",
        "output": "No",
        "category": "Toxic Language Detection 1463.json"
    },
    {
        "instruction": "Translate the given Spanish text to English",
        "input": "The present invention relates to a method of forming shape-retentive and shape-conforming aggregate wound dressings and biomaterials composed of gel nanoparticles and wound or bodily fluid in which the aggregates are held together by non-covalent bond physical forces such as, without limitation, hydrophobic-hydrophilic interactions and hydrogen bonds.",
        "output": "M\u00e9todo para formar ap\u00f3sitos para heridas y biomateriales agregados de forma adaptable y capaces de retener la forma, compuestos por un gel de nanopart\u00edculas y un fluido proveniente de una herida o un organismo, donde los agregados se mantienen unidos por fuerzas f\u00edsicas basadas en enlaces no covalentes, tales como, sin limitaciones, interacciones hidrof\u00f3bicas-hidrof\u00edli cas y enlaces hidr\u00f3geno.",
        "category": "Translation 1464.json"
    },
    {
        "instruction": "In this task, you are to Translate German text to English",
        "input": "Der Crossconnect besitzt weiter eine Raum-Schaltmatrix (S), die angepa\u00dft ist, Nachrichtensignale der niedrigsten Multiplexebene zu schalten.",
        "output": "Independent claims are also included for the following: a method of switching messages of different levels with a fixed bit rate.",
        "category": "Translation 1465.json"
    },
    {
        "instruction": "In this task, you need to Translate Czech text to English.",
        "input": "Vyn\u00e1lez rie\u0161i usporiadanie vysokotlak\u00e9ho  prep\u00fa\u0161\u0165acieho ventila vhodn\u00e9ho pre omedzovanie  pracovn\u00e9ho tlaku hydrogener\u00e1tora  s premenn\u00fdm geometrick\u00fdm objemom prostredn\u00edctvom  zm\u011bny geometrick\u00e9ho objemu.  Vysokotlak\u00fd prep\u00fa\u0161\u0165ac\u00ed ventil obsahuj\u00faci  teleso s prep\u00fa\u0161\u0165ac\u00edm otvorom ukon\u010den\u00fdm  sedlom pre uzatv\u00e1rac\u00ed pl\u00e9st tvo\u0159en\u00fd tvarovou  tesniacou plochou a driekom pre vedenie  pr\u00edtla\u010dnej pru\u017einy m\u00e1 driek ukon\u010den\u00fd vyva\u017eovac\u00edm  piestom veden\u00fdm v axi\u00e1ln\u011b nepohyblivom  valcovom otvore, ktor\u00fd je s prep\u00fa\u0161\u0165ac\u00edm  otvorom p\u0159epojen\u00fd spojovac\u00edm otvorom,  ktor\u00fd je vytvo\u0159en\u00fd v uzatv\u00e1racom  pieste.",
        "output": "The present invention provides a high pressure arrangement  a relief valve suitable for obstruction  working pressure of the pump  with variable geometric volume through  changes in geometric volume.  High Pressure Relief Valve Containing  body with discharge opening terminated  a saddle for a closure knit formed by a shape  a sealing surface and a guide shaft  the pressure spring has a shank terminated by balancing  a piston guided in an axially stationary manner  a cylindrical hole that is with the leak  through the opening through the connecting hole,  which is formed in a closure  pieste.",
        "category": "Translation 1466.json"
    },
    {
        "instruction": "Given a piece of financial news and its polarity, classify it into 'true' if the polarity is correct and classify into 'false' if the polarity is incorrect. Output must be 'true' or 'false'. ",
        "input": "news:The owners who have participated in the business operations of the company will continue in Poyry 's employment after the transaction .\npolarity:negative",
        "output": "false",
        "category": "Sentiment Analysis 1468.json"
    },
    {
        "instruction": "Given a passage with a question and an answer to that question, classify if the answer actually answers the question into 'yes' or 'no'. Output 'yes' if the answer answers the question and output 'no' if the answer does not answer the question.",
        "input": "Question: Does minimally invasive aortic valve replacement reduce atelectasis in cardiac intensive care?\nAnswer: Patients who had mini AVR had a significantly lower incidence of LLLA in the cardiac ICU than patients who had AVR through a full sternotomy.",
        "output": "yes",
        "category": "Answer Verification 1470.json"
    },
    {
        "instruction": "Given a passage classify if the passage has a definite objective/aim/goal or not. Output '1' if the passage has a defininte objective/aim/goal and output '0' if the passage does not have a definite objective/aim/goal.",
        "input": "To evaluate the influence of environmental enrichment (EE) on memory, cytokines, and brain-derived neurotrophic factor (BDNF) in the brain of adult rats subjected to experimental pneumococcal meningitis during infancy.', 'On postnatal day 11, the animals received either artificial cerebrospinal fluid (CSF) or Streptococcus pneumoniae suspension intracisternally at 1 \u00d7 10(6) CFU/mL and remained with their mothers until age 21 days. Animals were divided into the following groups: control, control + EE, meningitis, and meningitis + EE. EE began at 21 days and continued until 60 days of age (adulthood). EE consisted of a large cage with three floors, ramps, running wheels, and objects of different shapes and textures. At 60 days, animals were randomized and subjected to habituation to the open-field task and the step-down inhibitory avoidance task. After the tasks, the hippocampus and CSF were isolated for analysis.', 'The meningitis group showed no difference in performance between training and test sessions of the open-field task, suggesting habituation memory impairment; in the meningitis + EE group, performance was significantly different, showing preservation of habituation memory. In the step-down inhibitory avoidance task, there were no differences in behavior between training and test sessions in the meningitis group, showing aversive memory impairment; conversely, differences were observed in the meningitis + EE group, demonstrating aversive memory preservation. In the two meningitis groups, IL-4, IL-10, and BDNF levels were increased in the hippocampus, and BDNF levels in the CSF.",
        "output": "1",
        "category": "Intent Identification 1472.json"
    },
    {
        "instruction": "In this task you will be given a string and you should find the longest substring that is a palindrome. A palindrome is a string that is the same backwards as it is forwards. If the shortest possible palindrome is length 1 you should return the first character.",
        "input": "ccrcrckckcrck",
        "output": "crckckcrc",
        "category": "Program Execution 1474.json"
    },
    {
        "instruction": "In this task you will be given a list, of lists, of integers. For every inner list contained in the input list, you should multiply every even number in that list. The output should be a list of integers with the same length as the number of lists in the input list. If there are no even numbers in an inner list you should output 0 for that list.",
        "input": "[[-43, -12, 22, -39, 13], [8, 34], [17, -13, -5, -22, -50], [10, -8], [-19, 10], [30, 17], [44, 37, -33], [-18, -17, -9, -22, 2], [17, 38, 49]]",
        "output": "[-264, 272, 1100, -80, 10, 30, 44, 792, 38]",
        "category": "Program Execution 1475.json"
    },
    {
        "instruction": "In this task you will be given a list, of lists, of integers. For every inner list contained in the input list, you should multiply every odd number in that list. The output should be a list of integers with the same length as the number of lists in the input list. If there are no odd numbers in an inner list you should output 0 for that list.",
        "input": "[[-18, 21, -10, -1, -41], [36, -20, -37, 26, 12], [29, 39], [35, 28, 48], [-10, -42, 36, -47, 5], [8, -46], [28, 0, 22, -24], [-9, -32, 4], [-4, -41, 43, -1, 26], [29, 24, -26, 47], [29, -27, 17, -27, 47], [-24, 31, 49, 43, 14], [41, -27, -19, 46]]",
        "output": "[861, -37, 1131, 35, -235, 0, 0, -9, 1763, 1363, 16891659, 65317, 21033]",
        "category": "Program Execution 1476.json"
    },
    {
        "instruction": "In this task, you are given a sentence or phrase in English. You must translate it to Xhosa in a way that is equivalent in terms of meaning and grammatically correct.",
        "input": "The catapults are fired in rapid succession .",
        "output": "Izixhobo zokundulula inqwelo-moya zikhutshwa ngempumelelo ekhawulezileyo.",
        "category": "Translation 1498.json"
    },
    {
        "instruction": "In this task, you are given a sentence or phrase in Xhosa. You must translate it to English in a way that is equivalent in terms of meaning and grammatically correct.",
        "input": "Nanina xa zithotywa zisiwa endaweni, ubunzima bale platifomu neleli buthathwa ngomlinganiselo ngeflegi ende emxinwa yenqanawa",
        "output": "When lowered into position, the weight of this platform and the ladder are taken by a fitted pendant.",
        "category": "Translation 1499.json"
    },
    {
        "instruction": "Given an open-ended topic (movie name, a persons name, an event, sports, etc) generate a simple trivia-type question.",
        "input": "anastasio somoza debayle",
        "output": "In 1936, Anastasio Somoza became the dictator of which country?, Jos Santos Zelaya, William Walker, Adolfo Daz, Emiliano Chamorro, Juan Bautista Sacasa, Anastasio Somoza Garca, Luis Somoza, Violeta Chamorro, Enrique Bolaos and Daniel Ortega are associated with the politics of which country?",
        "category": "Question Generation 1516.json"
    },
    {
        "instruction": "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.",
        "input": "Which singer and actress, married to Lee Mead, gave birth to baby Betsy on May 1st.?",
        "output": "denise van outen",
        "category": "Question Answering 1517.json"
    },
    {
        "instruction": "Given a factoid/trivia type question, generate the topic of the question. The topic is the entity the question talks about.",
        "input": "Who sang with the Animals?",
        "output": "the animals",
        "category": "Question Understanding 1518.json"
    },
    {
        "instruction": "Given a trivia question, classify broad topical category from this list: 'theater', 'geology', 'book', 'tv', 'astronomy', 'aviation', 'military', 'government', 'boxing', 'projects', 'metropolitan_transit', 'law', 'venture_capital', 'broadcast', 'biology', 'people', 'influence', 'baseball', 'spaceflight', 'media_common', 'cvg', 'opera', 'olympics', 'chemistry', 'visual_art', 'conferences', 'sports', 'language', 'travel', 'location', 'award', 'dining', 'martial_arts', 'comic_strips', 'computer', 'user', 'tennis', 'music', 'organization', 'food', 'event', 'transportation', 'fictional_universe', 'measurement_unit', 'meteorology', 'distilled_spirits', 'symbols', 'architecture', 'freebase', 'internet', 'fashion', 'boats', 'cricket', 'film', 'medicine', 'finance', 'comic_books', 'celebrities', 'soccer', 'games', 'time', 'geography', 'interests', 'common', 'base', 'business', 'periodicals', 'royalty', 'education', 'type', 'religion', 'automotive', 'exhibitions'.",
        "input": "General Victoriano Huerta, Emiliano Zapata and Pancho Villa feature in the history of which country?",
        "output": "people",
        "category": "Question Understanding 1519.json"
    },
    {
        "instruction": "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.",
        "input": "&#128557;&#128557;&#128557; RT @VineForTheByrd: Bae: go text your hoes \nMe: https://t.co/5PAfEceL1i",
        "output": "Offensive",
        "category": "Toxic Language Detection 1523.json"
    },
    {
        "instruction": "You are given a text of the tweet and a corresponding label whether this tweet is 'Offensive', 'Hate Speech' or 'Neither'. Your job is to identify if the label is correct. Generate label 'true' if it's correct, 'false' otherwise.",
        "input": "Tweet: 7 pounds never fails to make me cry. Im not bitch, I just relate to it\nLabel: Hate Speech",
        "output": "false",
        "category": "Toxic Language Detection 1524.json"
    },
    {
        "instruction": "You are provided with an \"Event\" and it's \"Intent\" related to PersonX. Determine the sentiment value of the given input as either \"Positive\", \"Negative\", and \"Unknown\". ",
        "input": "Event:PersonX makes PersonY very sad. Intent: 1) to be informed",
        "output": "Negative",
        "category": "Sentiment Analysis 1539.json"
    },
    {
        "instruction": "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",
        "input": "Event:PersonX tells my husband. Intent:. XEmotion: 1) glad 2) relieved",
        "output": "upset.",
        "category": "Misc. 1540.json"
    },
    {
        "instruction": "Given an English language product review, determine if it is a Good Review or a Bad Review. A good review is one where the product's review has positive tone and Bad review is one where the tone of product's review is negative.",
        "input": "Love them. Easy install.",
        "output": "Good Review",
        "category": "Sentiment Analysis 1545.json"
    },
    {
        "instruction": "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.",
        "input": "Premise: PersonX takes the test again\nHypothesis: Because PersonX wanted to do better this time\nUpdate: They got a C the first time",
        "output": "strengthener",
        "category": "Textual Entailment 1551.json"
    },
    {
        "instruction": "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, that is, it makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis, that is, it makes you much more likely to believe the hypothesis is true. Your task is to answer with 'strengthener' or 'weakener' if the update strengthens or weakens the hypothesis, respectively.",
        "input": "Premise: Skater riding skateboard on a quarter pipe while the crowd watches.\nHypothesis: Skater riding nice skateboard on a quarter pipe while the crowd watches.\nUpdate: The skater is covered in dirt",
        "output": "weakener",
        "category": "Textual Entailment 1552.json"
    },
    {
        "instruction": "In this task, you are given a hypothesis and an update. The hypothesis sentence is a statement that speaks of a socially normative behavior. In other words, it is a generalizing statement about how we expect people to behave in society. The update provides additional contexts about the situation that might UNDERMINE or SUPPORT the generalization. An undermining context provides a situation that weakens the hypothesis. A supporting context provides a situation that strengthens the generalization. Your task is to output 'strengthener' or 'weakener' if the update supports or undermines the hypothesis, respectively",
        "input": "Hypothesis: It's okay to be angry if your neighbors disturb you.\nUpdate: They are in danger and need your help.",
        "output": "weakener",
        "category": "Textual Entailment 1553.json"
    },
    {
        "instruction": "You are given a statement written in Bengali. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement . Output the word from the correct option .",
        "input": "Statement: \u0993\u09af\u09bc\u09c7\u09b2\u09bf\u09a8 \u09b8\u09c1\u0987\u09a1\u09c7\u09a8\u09c7\u09b0 \u09aa\u09be\u099c\u09be\u09b2\u09be \u09a8\u09be\u09ae\u0995 \u098f\u0995\u099f\u09bf \u099b\u09cb\u099f\u09cd\u099f \u0997\u09cd\u09b0\u09be\u09ae\u09c7 \u09e7\u09ef\u09ee\u09ea \u09b8\u09be\u09b2\u09c7\u09b0 \u09e8\u09ea \u099c\u09c1\u09a8 \u099c\u09a8\u09cd\u09ae\u0997\u09cd\u09b0\u09b9\u09a3 \u0995\u09b0\u09c7\u09a8\u0964 \u0997\u09cd\u09b0\u09be\u09ae\u099f\u09bf \u09b8\u09c1\u09ae\u09c7\u09b0\u09c1 \u09ac\u09c3\u09a4\u09cd\u09a4 \u09a5\u09c7\u0995\u09c7 \u09e7\u09e6\u09e6 \u0995\u09bf\u09b2\u09cb\u09ae\u09bf\u099f\u09be\u09b0 \u0989\u09a4\u09cd\u09a4\u09b0\u09c7 <MASK>-\u09b8\u09c1\u0987\u09a1\u09c7\u09a8 \u09b8\u09c0\u09ae\u09be\u09a8\u09cd\u09a4\u09c7\u09b0 \u0995\u09be\u099b\u09be\u0995\u09be\u099b\u09bf \u0985\u09ac\u09b8\u09cd\u09a5\u09bf\u09a4\u0964 \u09a4\u09bf\u09a8\u09bf \u09b8\u09c1\u0987\u09a1\u09bf\u09b6 \u09b2\u09c0\u0997\u09c7 \u099f\u09b0\u09ac\u09cb\u09a6\u09be \u0986\u0987.\u0995\u09c7.-\u098f\u09b0 \u09b9\u09af\u09bc\u09c7 \u09ab\u09c1\u099f\u09ac\u09b2 \u0996\u09c7\u09b2\u09a4\u09c7\u09a8\u0964 \u09b6\u09c0\u09a4\u0995\u09be\u09b2\u09c7 \u09a4\u09be\u09b0 \u09b8\u09cd\u09a8\u09cb\u09ac\u09cb\u09b0\u09cd\u09a1\u09bf\u0982\u09af\u09bc\u09c7\u09b0 \u09b6\u0996 \u099b\u09bf\u09b2, \u09e8\u09e6\u09e6\u09ea \u09b8\u09be\u09b2\u09c7 \u0997\u09cb\u09a5\u09be\u09b0\u09cd\u09a8\u09ac\u09be\u0997\u09c7 \u098f\u0995\u099f\u09bf \u09b8\u09cd\u09a8\u09cb\u09ac\u09cb\u09b0\u09cd\u09a1\u09bf\u0982 \u09aa\u09cd\u09b0\u09a4\u09bf\u09af\u09cb\u0997\u09bf\u09a4\u09be\u09af\u09bc \u0996\u09be\u09b0\u09be\u09aa \u09aa\u09a4\u09a8\u09c7\u09b0 \u09ab\u09b2\u09c7 \u09a4\u09bf\u09a8\u09bf \u0986\u0998\u09be\u09a4\u09aa\u09cd\u09b0\u09be\u09aa\u09cd\u09a4 \u09b9\u09a8 \u098f\u09ac\u0982 \u09a4\u09be\u09b0 \u0995\u09cb\u09ae\u09b0\u09c7\u09b0 \u09ac\u09be\u09ae\u09a6\u09bf\u0995\u09c7\u09b0 \u09a8\u09bf\u099a\u09c7\u09b0 \u0985\u0982\u09b6 \u09aa\u09cd\u09af\u09be\u09b0\u09be\u09b2\u09be\u0987\u09b8\u09cd\u099f \u09b9\u09af\u09bc\u0964 \u098f\u09b0\u09aa\u09b0 \u09a4\u09bf\u09a8\u09bf \u09b9\u09c1\u09cd\u0987\u09b2\u099a\u09c7\u09af\u09bc\u09be\u09b0 \u09ac\u09be\u09b8\u09cd\u0995\u09c7\u099f\u09ac\u09b2\u0995\u09c7 \u09aa\u09c7\u09b6\u09be \u09b9\u09bf\u09b8\u09be\u09ac\u09c7 \u0997\u09cd\u09b0\u09b9\u09a3 \u0995\u09b0\u09c7\u09a8 \u098f\u09ac\u0982 \u09b8\u09c1\u0987\u09a1\u09bf\u09b6 \u09b2\u09c0\u0997\u09c7 \u099c\u09bf.\u0986\u09b0.\u09ac\u09bf.\u0995\u09c7. \u0997\u09cb\u09a5\u09be\u09b0\u09cd\u09a8\u09ac\u09be\u0997-\u098f\u09b0 \u09b9\u09af\u09bc\u09c7 \u0996\u09c7\u09b2\u09c7\u09a8\u0964 \u0995\u09bf\u09a8\u09cd\u09a4\u09c1 \u09b8\u09c1\u0987\u09a1\u09c7\u09a8\u09c7 \u0995\u09cb\u09a8 \u099c\u09be\u09a4\u09c0\u09af\u09bc \u09ae\u09b9\u09bf\u09b2\u09be \u09a6\u09b2 \u099b\u09bf\u09b2 \u09a8\u09be\u0964 \u09a4\u09bf\u09a8\u09bf \u0987\u09a8\u09cd\u09b8\u09ac\u09cd\u09b0\u09c1\u0995\u09c7 \u09a6\u09c1\u099f\u09bf \u09b8\u09c7\u09ae\u09bf\u09b8\u09cd\u099f\u09be\u09b0\u09c7 \u099c\u09be\u09b0\u09cd\u09ae\u09be\u09a8 \u09b6\u09c7\u0996\u09c7\u09a8, \u0995\u09bf\u09a8\u09cd\u09a4\u09c1 \u09b8\u09c7\u0996\u09be\u09a8\u09c7\u0993 \u09b9\u09c1\u0987\u09b2\u099a\u09c7\u09af\u09bc\u09be\u09b0 \u09ac\u09be\u09b8\u09cd\u0995\u09c7\u099f\u09ac\u09b2 \u09a6\u09b2 \u099b\u09bf\u09b2 \u09a8\u09be\u0964\n\n Option A: \u09a8\u09c7\u09a6\u09be\u09b0\u09b2\u09cd\u09af\u09be\u09a8\u09cd\u09a1\u0995\u09c7\n\n Option B: \u09ab\u09bf\u09a8\u09b2\u09cd\u09af\u09be\u09a8\u09cd\u09a1\n\n Option C: \u09ac\u09cd\u09b0\u09be\u099c\u09bf\u09b2\n\n Option D: \u0995\u09be\u09a8\u09be\u09a1\u09be",
        "output": "\u09ab\u09bf\u09a8\u09b2\u09cd\u09af\u09be\u09a8\u09cd\u09a1",
        "category": "Fill in The Blank 1561.json"
    },
    {
        "instruction": "You are given a statement written in Gujarati. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .",
        "input": "Statement: \u0ab9\u0abe\u0aa5\u0ac0 (\u0aa4\u0abe. \u0aa6\u0acd\u0ab5\u0abe\u0ab0\u0a95\u0abe) <MASK> \u0aa6\u0ac7\u0ab6\u0aa8\u0abe \u0aaa\u0ab6\u0acd\u0a9a\u0abf\u0aae \u0aad\u0abe\u0a97\u0aae\u0abe\u0a82 \u0a86\u0ab5\u0ac7\u0ab2\u0abe  \u0a97\u0ac1\u0a9c\u0ab0\u0abe\u0aa4 \u0ab0\u0abe\u0a9c\u0acd\u0aaf\u0aa8\u0abe \u0ab8\u0acc\u0ab0\u0abe\u0ab7\u0acd\u0a9f\u0acd\u0ab0 \u0ab5\u0abf\u0ab8\u0acd\u0aa4\u0abe\u0ab0\u0aae\u0abe\u0a82 \u0a86\u0ab5\u0ac7\u0ab2\u0abe \u0aa6\u0ac7\u0ab5\u0aad\u0ac2\u0aae\u0abf \u0aa6\u0acd\u0ab5\u0abe\u0ab0\u0a95\u0abe \u0a9c\u0abf\u0ab2\u0acd\u0ab2\u0abe\u0aae\u0abe\u0a82 \u0a86\u0ab5\u0ac7\u0ab2\u0abe \u0aa4\u0ac7\u0aae\u0a9c \u0aa4\u0acd\u0ab0\u0aa3 \u0aac\u0abe\u0a9c\u0ac1\u0a8f\u0aa5\u0ac0 \u0aa6\u0ab0\u0abf\u0aaf\u0abe \u0ab5\u0aa1\u0ac7 \u0a98\u0ac7\u0ab0\u0abe\u0aaf\u0ac7\u0ab2\u0abe \u0a93\u0a96\u0abe\u0aae\u0a82\u0aa1\u0ab3 \u0aa4\u0ab0\u0ac0\u0a95\u0ac7 \u0a93\u0ab3\u0a96\u0abe\u0aa4\u0abe \u0aa6\u0acd\u0ab5\u0abe\u0ab0\u0a95\u0abe \u0aa4\u0abe\u0ab2\u0ac1\u0a95\u0abe\u0aae\u0abe\u0a82 \u0a86\u0ab5\u0ac7\u0ab2\u0ac1\u0a82 \u0a8f\u0a95  \u0a97\u0abe\u0aae \u0a9b\u0ac7. \u0ab9\u0abe\u0aa5\u0ac0 \u0a97\u0abe\u0aae\u0aa8\u0abe \u0ab2\u0acb\u0a95\u0acb\u0aa8\u0acb \u0aae\u0ac1\u0a96\u0acd\u0aaf \u0ab5\u0acd\u0aaf\u0ab5\u0ab8\u0abe\u0aaf \u0a96\u0ac7\u0aa4\u0ac0, \u0aae\u0abe\u0a9b\u0ac0\u0aae\u0abe\u0ab0\u0ac0 \u0aa4\u0ac7\u0aae \u0a9c \u0aaa\u0ab6\u0ac1\u0aaa\u0abe\u0ab2\u0aa8 \u0a9b\u0ac7. \u0a86 \u0a97\u0abe\u0aae\u0aae\u0abe\u0a82 \u0aae\u0ac1\u0a96\u0acd\u0aaf\u0aa4\u0acd\u0ab5\u0ac7 \u0a98\u0a89\u0a82, \u0a9c\u0ac0\u0ab0\u0ac1, \u0aae\u0a97\u0aab\u0ab3\u0ac0, \u0aa4\u0ab2, \u0aac\u0abe\u0a9c\u0ab0\u0ac0, \u0a9a\u0aa3\u0abe, \u0a95\u0aaa\u0abe\u0ab8,  \u0aa6\u0abf\u0ab5\u0ac7\u0ab2\u0abe, \u0ab0\u0a9c\u0a95\u0acb \u0aa4\u0ac7\u0aae \u0a9c \u0a85\u0aa8\u0acd\u0aaf \u0ab6\u0abe\u0a95\u0aad\u0abe\u0a9c\u0ac0\u0aa8\u0abe \u0aaa\u0abe\u0a95\u0aa8\u0ac0 \u0a96\u0ac7\u0aa4\u0ac0 \u0a95\u0ab0\u0ab5\u0abe\u0aae\u0abe\u0a82 \u0a86\u0ab5\u0ac7 \u0a9b\u0ac7. \u0a86 \u0a97\u0abe\u0aae\u0aae\u0abe\u0a82 \u0aaa\u0acd\u0ab0\u0abe\u0aa5\u0aae\u0abf\u0a95 \u0ab6\u0abe\u0ab3\u0abe, \u0aaa\u0a82\u0a9a\u0abe\u0aaf\u0aa4\u0a98\u0ab0, \u0a86\u0a82\u0a97\u0aa3\u0ab5\u0abe\u0aa1\u0ac0 \u0aa4\u0ac7\u0aae \u0a9c \u0aa6\u0ac2\u0aa7\u0aa8\u0ac0 \u0aa1\u0ac7\u0ab0\u0ac0 \u0a9c\u0ac7\u0ab5\u0ac0 \u0ab8\u0ab5\u0ab2\u0aa4\u0acb \u0aaa\u0acd\u0ab0\u0abe\u0aaa\u0acd\u0aaf \u0aa5\u0aaf\u0ac7\u0ab2\u0ac0 \u0a9b\u0ac7.\n\n Option A: \u0aaa\u0a82\u0a9a\u0abe\u0aaf\u0aa4\u0a98\u0ab0\n\n Option B: \u0ab8\u0acc\u0ab0\u0abe\u0ab7\u0acd\u0a9f\u0acd\u0ab0\n\n Option C: \u0a86\u0a82\u0a97\u0aa3\u0ab5\u0abe\u0aa1\u0ac0\n\n Option D: \u0aad\u0abe\u0ab0\u0aa4",
        "output": "\u0aad\u0abe\u0ab0\u0aa4",
        "category": "Fill in The Blank 1562.json"
    },
    {
        "instruction": "You are given a statement written in Hindi. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .",
        "input": "Statement: <MASK>, \u0905\u0932\u094d\u0932\u093e\u092a\u0941\u0930, \u0936\u092e\u094d\u092d\u0942\u0928\u0917\u0932\u093e, \u092c\u0930\u093e\u092c\u093f\u0915\u0942, \u092a\u0948\u0925\u093e\u0928, \u0909\u0932\u093f\u092f\u093e\u092a\u0941\u0930, \u092a\u0926\u092e\u0928\u0917\u0932\u093e, \u0906\u091c\u092e\u092a\u0941\u0930, \u0939\u091c\u093f\u092f\u093e\u0901\u092a\u0941\u0930, \u0915\u093f\u0928\u094d\u0928\u0930 \u0928\u0917\u0932\u093e, \u0939\u091c\u0930\u0924\u092a\u0941\u0930, \u0932\u0932\u0908, \u0928\u0935\u093e\u092c\u0917\u0902\u091c, \u092e\u0902\u091d\u0928\u093e, \u0930\u0938\u0940\u0926\u093e\u092c\u093e\u0926, \u092c\u0930\u0908, \u092c\u0947\u0932\u093e (\u0917\u093e\u0901\u0935), \u0939\u0930\u0938\u093f\u0902\u0939\u092a\u0941\u0930 \u0917\u094b\u0935\u093e, \u0930\u0938\u0940\u0926\u093e\u092c\u093e\u0926, \u0930\u0941\u091f\u0949\u0932, \u0932\u0941\u0916\u0921\u093c\u092a\u0941\u0930\u093e, \u092e\u0941\u0930\u093e\u0920\u0940, \u0930\u092e\u093e\u092a\u0941\u0930, \u092b\u0930\u0940\u0926\u092a\u0941\u0930, \u0917\u0920\u0935\u093e\u092f\u093e, \u0938\u093f\u0932\u0938\u0902\u0921\u093e, \u092c\u093f\u0930\u093e\u0907\u092e\u092a\u0941\u0930, \u092a\u0930\u094c\u0932\u0940, \u092d\u091f\u093e\u0938\u093e, \u0905\u0902\u0917\u0930\u0948\u092f\u093e,\n\n Option A: \u0930\u0938\u0940\u0926\u093e\u092c\u093e\u0926\n\n Option B: \u092a\u0926\u092e\u0928\u0917\u0932\u093e\n\n Option C: \u0905\u0932\u094d\u0932\u093e\u092a\u0941\u0930\n\n Option D: \u092e\u0926\u093e\u0930\u092a\u0941\u0930",
        "output": "\u092e\u0926\u093e\u0930\u092a\u0941\u0930",
        "category": "Fill in The Blank 1563.json"
    },
    {
        "instruction": "You are given a statement written in Kannada. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .",
        "input": "Statement: <MASK> \u0ca6\u0cc7\u0cb6\u0c95\u0ccd\u0c95\u0cc6 \u0cb9\u0cbf\u0c82\u0ca6\u0cbf\u0cb0\u0cc1\u0c97\u0cbf\u0ca6 \u0ca8\u0c82\u0ca4\u0cb0 \u0cac\u0cc6\u0c82\u0c97\u0cb3\u0cc2\u0cb0\u0cc1 \u0cae\u0cb9\u0cbe\u0ca7\u0cb0\u0ccd\u0cae\u0caa\u0cc0\u0ca0\u0ca6 \u0c95\u0cc1\u0cb2\u0caa\u0ca4\u0cbf\u0caf\u0cbe\u0c97\u0cbf \u0ca8\u0cc7\u0cae\u0c95\u0c97\u0cca\u0c82\u0ca1\u0cb0\u0cc1. \u0ca8\u0c82\u0ca4\u0cb0 \u0c95\u0cac\u0ccd\u0cac\u0ca8\u0ccd \u0caa\u0cc7\u0c9f\u0cc6\u0caf \u0cb2\u0cc2\u0cb0\u0ccd\u0ca6\u0cc1\u0caa\u0cbe\u0ca0\u0cb6\u0cbe\u0cb2\u0cc6, \u0cb8\u0cb0\u0ccd\u0cb5\u0c9c\u0ccd\u0c9e\u0ca8\u0c97\u0cb0\u0ca6 \u0c85\u0cb2\u0ccb\u0cb6\u0cbf\u0caf\u0cb8\u0ccd \u0caa\u0ccd\u0cb0\u0ccc\u0ca2\u0cb6\u0cbe\u0cb2\u0cc6 \u0cb9\u0cbe\u0c97\u0cc2 \u0cb9\u0cb2\u0cb8\u0cc2\u0cb0\u0cbf\u0ca8 \u0cb2\u0cc2\u0cb0\u0ccd\u0ca6\u0cc1 \u0caa\u0ccd\u0cb0\u0ccc\u0ca2\u0cb6\u0cbe\u0cb2\u0cc6\u0c97\u0cb3 \u0caa\u0ccd\u0cb0\u0cbe\u0c9a\u0cbe\u0cb0\u0ccd\u0caf\u0cb0\u0cbe\u0c97\u0cbf \u0c95\u0cbe\u0cb0\u0ccd\u0caf\u0ca8\u0cbf\u0cb0\u0ccd\u0cb5\u0cb9\u0cbf\u0cb8\u0cbf \u0cb8\u0cbe\u0cb5\u0cbf\u0cb0\u0cbe\u0cb0\u0cc1 \u0cb5\u0cbf\u0ca6\u0ccd\u0caf\u0cbe\u0cb0\u0ccd\u0ca5\u0cbf\u0c97\u0cb3 \u0cac\u0cbe\u0cb3\u0cac\u0cc6\u0cb3\u0c95\u0cbe\u0ca6\u0cb0\u0cc1. \u0c95\u0cc6\u0cb2\u0c95\u0cbe\u0cb2 \u0c95\u0cb0\u0ccd\u0ca8\u0cbe\u0c9f\u0c95\u0ca4\u0cbe\u0cb0\u0cc6 \u0cae\u0cbe\u0cb8\u0cbf\u0c95\u0ca6 \u0cb8\u0c82\u0caa\u0cbe\u0ca6\u0c95\u0cb0\u0cc2 \u0c86\u0c97\u0cbf\u0ca6\u0ccd\u0ca6\u0cb0\u0cc1. \u0c8e\u0cb0\u0ca1\u0ca8\u0cc7 \u0cb5\u0ccd\u0caf\u0cbe\u0c9f\u0cbf\u0c95\u0ca8\u0ccd \u0cb8\u0cae\u0cbe\u0cb5\u0cc7\u0cb6\u0ca6 \u0ca8\u0cbf\u0cb0\u0ccd\u0ca3\u0caf\u0c97\u0cb3\u0cc1 \u0cb9\u0cca\u0cb0\u0cac\u0cb0\u0cc1\u0ca4\u0ccd\u0ca4\u0cbf\u0ca6\u0ccd\u0ca6\u0c82\u0ca4\u0cc6 \u0c95\u0ca8\u0ccd\u0ca8\u0ca1\u0ca6\u0cb2\u0ccd\u0cb2\u0cbf \u0ca7\u0cbe\u0cb0\u0ccd\u0cae\u0cbf\u0c95 \u0cb8\u0cbe\u0cb9\u0cbf\u0ca4\u0ccd\u0caf\u0cb5\u0ca8\u0ccd\u0ca8\u0cc1 \u0cb6\u0ccd\u0cb0\u0cc0\u0cae\u0c82\u0ca4\u0c97\u0cca\u0cb3\u0cbf\u0cb8\u0cc1\u0cb5 \u0ca8\u0cbf\u0c9f\u0ccd\u0c9f\u0cbf\u0ca8\u0cb2\u0ccd\u0cb2\u0cbf \u0c87\u0cb5\u0cb0\u0cc1 \u0cb8\u0ccd\u0cb5\u0caa\u0ccd\u0cb0\u0cc7\u0cb0\u0ca3\u0cc6\u0caf\u0cbf\u0c82\u0ca6 \u0cb0\u0c9a\u0cbf\u0cb8\u0cbf\u0ca6 / \u0c85\u0ca8\u0cc1\u0cb5\u0cbe\u0ca6\u0cbf\u0cb8\u0cbf\u0ca6 / \u0cb8\u0c82\u0caa\u0cbe\u0ca6\u0cbf\u0cb8\u0cbf\u0ca6 \u0c95\u0cc3\u0ca4\u0cbf\u0c97\u0cb3\u0cc1 \u0c87\u0c82\u0ca6\u0cbf\u0c97\u0cc2 \u0c95\u0ca8\u0ccd\u0ca8\u0ca1 \u0c95\u0ca5\u0ccb\u0cb2\u0cbf\u0c95 \u0c9c\u0ca8\u0cae\u0cbe\u0ca8\u0cb8\u0ca6\u0cb2\u0ccd\u0cb2\u0cbf \u0c85\u0cae\u0cb0\u0cb5\u0cbe\u0c97\u0cbf\u0cb5\u0cc6 \u0cb9\u0cbe\u0c97\u0cc2 \u0caa\u0ccd\u0cb0\u0cc7\u0cb0\u0ca3\u0cbe\u0ca4\u0ccd\u0cae\u0c95\u0cb5\u0cbe\u0c97\u0cbf\u0cb5\u0cc6. \u0cac\u0cc6\u0c82\u0c97\u0cb3\u0cc2\u0cb0\u0cc1  \u0cae\u0cb9\u0cbe\u0ca7\u0cb0\u0ccd\u0cae\u0caa\u0cc0\u0ca0\u0ca6 \u0cb6\u0cbf\u0c95\u0ccd\u0cb7\u0ca3\u0cae\u0c82\u0ca1\u0cb2\u0cbf\u0caf \u0c95\u0cbe\u0cb0\u0ccd\u0caf\u0ca6\u0cb0\u0ccd\u0cb6\u0cbf\u0caf\u0cbe\u0c97\u0cbf\u0ca6\u0ccd\u0ca6\u0cbe\u0c97 \u0c87\u0cb5\u0cb0 \u0caa\u0ccd\u0cb0\u0caf\u0ca4\u0ccd\u0ca8\u0ca6\u0cbf\u0c82\u0ca6\u0cbe\u0c97\u0cbf \u0c97\u0ccd\u0cb0\u0cbe\u0cae\u0cbe\u0c82\u0ca4\u0cb0 \u0caa\u0ccd\u0cb0\u0ca6\u0cc7\u0cb6\u0c97\u0cb3\u0cb2\u0ccd\u0cb2\u0cbf \u0c85\u0c82\u0ca6\u0cb0\u0cc6 \u0ca4\u0c82\u0cac\u0cc1\u0c9a\u0cc6\u0c9f\u0ccd\u0c9f\u0cbf\u0caa\u0cbe\u0cb3\u0ccd\u0caf, \u0cac\u0cc7\u0c97\u0cc2\u0cb0\u0cc1, \u0cb9\u0cbe\u0cb0\u0ccb\u0cac\u0cc6\u0cb2\u0cc6, \u0cae\u0cb0\u0cbf\u0caf\u0cbe\u0caa\u0cc1\u0cb0, \u0cb6\u0cbf\u0cb2\u0ccd\u0cb5\u0cc6\u0caa\u0cc1\u0cb0 \u0cae\u0cc1\u0c82\u0ca4\u0cbe\u0ca6\u0cc6\u0ca1\u0cc6\u0c97\u0cb3\u0cb2\u0ccd\u0cb2\u0cbf \u0caa\u0ccd\u0cb0\u0ccc\u0ca2\u0cb6\u0cbe\u0cb2\u0cc6\u0c97\u0cb3\u0cc1 \u0caa\u0ccd\u0cb0\u0cbe\u0cb0\u0c82\u0cad\u0cb5\u0cbe\u0ca6\u0cb5\u0cc1.\n\n Option A: \u0c95\u0cb0\u0ccd\u0ca8\u0cbe\u0c9f\u0c95\n\n Option B: \u0c87\u0c82\u0ca1\u0cbf\u0caf\u0cbe\n\n Option C: \u0cb0\u0ccb\u0cae\u0cbf\n\n Option D: \u0cac\u0cc6\u0c82\u0c97\u0cb3\u0cc2\u0cb0\u0cc1",
        "output": "\u0c87\u0c82\u0ca1\u0cbf\u0caf\u0cbe",
        "category": "Fill in The Blank 1564.json"
    },
    {
        "instruction": "You are given a statement written in Malayalam. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .",
        "input": "Statement: \u0d38\u0d43\u0d37\u0d4d\u0d1f\u0d3f\u0d2f\u0d3f\u0d32\u0d46 \u0d38\u0d57\u0d2d\u0d3e\u0d17\u0d4d\u0d2f\u0d3e\u0d35\u0d38\u0d4d\u0d25\u0d2f\u0d3f\u0d7d \u0d28\u0d3f\u0d28\u0d4d\u0d28\u0d41\u0d33\u0d4d\u0d33 \u0d2e\u0d28\u0d41\u0d37\u0d4d\u0d2f\u0d28\u0d4d\u0d31\u0d46 \u0d2a\u0d24\u0d28\u0d24\u0d4d\u0d24\u0d46\u0d15\u0d4d\u0d15\u0d41\u0d31\u0d3f\u0d1a\u0d4d\u0d1a\u0d41\u0d33\u0d4d\u0d33 \u0d15\u0d4d\u0d30\u0d3f\u0d38\u0d4d\u0d24\u0d40\u0d2f \u0d15\u0d25\u0d2f\u0d3e\u0d23\u0d4d\u200c \u0d15\u0d3e\u0d35\u0d4d\u0d2f\u0d24\u0d4d\u0d24\u0d3f\u0d28\u0d4d\u0d31\u0d46 \u0d35\u0d3f\u0d37\u0d2f\u0d02:  \u0d08 \u0d15\u0d25\u0d2f\u0d3f\u0d7d, \u0d06\u0d26\u0d3f\u0d2e\u0d3e\u0d24\u0d3e\u0d2a\u0d3f\u0d24\u0d3e\u0d15\u0d4d\u0d15\u0d33\u0d3e\u0d2f \u0d06\u0d26\u0d02-\u0d39\u0d35\u0d4d\u0d35\u0d3e\u0d2e\u0d7c, \u0d05\u0d27\u0d03\u0d2a\u0d24\u0d3f\u0d1a\u0d4d\u0d1a \u0d2e\u0d3e\u0d32\u0d3e\u0d16\u0d2f\u0d3e\u0d2f \u0d38\u0d3e\u0d24\u0d4d\u0d24\u0d3e\u0d28\u0d4d\u0d31\u0d46 \u0d2a\u0d4d\u0d30\u0d32\u0d4b\u0d2d\u0d28\u0d24\u0d4d\u0d24\u0d3f\u0d7d \u0d35\u0d40\u0d23\u0d24\u0d3f\u0d28\u0d46 \u0d24\u0d41\u0d1f\u0d7c\u0d28\u0d4d\u0d28\u0d4d \u0d2d\u0d57\u0d2e\u0d3f\u0d15\u0d2a\u0d31\u0d41\u0d26\u0d40\u0d38\u0d2f\u0d3f\u0d7d \u0d28\u0d3f\u0d28\u0d4d\u0d28\u0d41 \u0d2c\u0d39\u0d3f\u0d37\u0d4d\u0d15\u0d30\u0d3f\u0d15\u0d4d\u0d15\u0d2a\u0d4d\u0d2a\u0d46\u0d1f\u0d41\u0d28\u0d4d\u0d28\u0d41.   \"\u0d26\u0d48\u0d35\u0d3f\u0d15 \u0d35\u0d34\u0d3f\u0d15\u0d33\u0d41\u0d1f\u0d46 \u0d28\u0d40\u0d24\u0d3f \u0d2e\u0d28\u0d41\u0d37\u0d4d\u0d2f\u0d7c\u0d15\u0d4d\u0d15\u0d41 \u0d35\u0d3f\u0d35\u0d30\u0d3f\u0d1a\u0d4d\u0d1a\u0d41\u0d15\u0d4a\u0d1f\u0d41\u0d15\u0d4d\u0d15\u0d41\u0d15\u0d2f\u0d41\u0d02  \u0d26\u0d48\u0d35\u0d24\u0d4d\u0d24\u0d3f\u0d28\u0d4d\u0d31\u0d46 \u0d05\u0d24\u0d3f\u0d30\u0d3f\u0d32\u0d4d\u0d32\u0d3e\u0d24\u0d4d\u0d24 \u0d26\u0d40\u0d7c\u0d18\u0d26\u0d43\u0d37\u0d4d\u0d1f\u0d3f\u0d2f\u0d41\u0d02 \u0d2e\u0d28\u0d41\u0d37\u0d4d\u0d2f\u0d28\u0d4d\u0d31\u0d46 \u0d07\u0d1a\u0d4d\u0d1b\u0d3e\u0d38\u0d4d\u0d35\u0d3e\u0d24\u0d28\u0d4d\u0d24\u0d4d\u0d30\u0d4d\u0d2f\u0d35\u0d41\u0d02 \u0d24\u0d2e\u0d4d\u0d2e\u0d3f\u0d32\u0d41\u0d33\u0d4d\u0d33 \u0d38\u0d02\u0d18\u0d7c\u0d37\u0d02 \u0d1a\u0d3f\u0d24\u0d4d\u0d30\u0d40\u0d15\u0d30\u0d3f\u0d15\u0d4d\u0d15\u0d41\u0d15\u0d2f\u0d41\u0d02\u200c\" \u0d06\u0d23\u0d4d\u200c \u0d24\u0d28\u0d4d\u0d31\u0d46 \u0d32\u0d15\u0d4d\u0d37\u0d4d\u0d2f\u0d2e\u0d46\u0d28\u0d4d\u0d28\u0d4d \u0d15\u0d43\u0d24\u0d3f\u0d2f\u0d41\u0d1f\u0d46 \u0d12\u0d28\u0d4d\u0d28\u0d3e\u0d02 \u0d2a\u0d41\u0d38\u0d4d\u0d24\u0d15\u0d24\u0d4d\u0d24\u0d3f\u0d7d <MASK> \u0d35\u0d4d\u0d2f\u0d15\u0d4d\u0d24\u0d2e\u0d3e\u0d15\u0d4d\u0d15\u0d41\u0d28\u0d4d\u0d28\u0d41 .\n\n Option A: \u0d2e\u0d3f\u0d7d\u0d1f\u0d4d\u0d1f\u0d7a\n\n Option B: Rekha\n\n Option C: \u0d2e\u0d3f\u0d7d\u0d1f\u0d4d\u0d1f\u0d28\u0d4d\u0d31\u0d46\n\n Option D: \u0d35\u0d3f\u0d7c\u0d1c\u0d3f\u0d32\u0d3f\u0d28\u0d4d\u0d31\u0d46",
        "output": "\u0d2e\u0d3f\u0d7d\u0d1f\u0d4d\u0d1f\u0d7a",
        "category": "Fill in The Blank 1565.json"
    },
    {
        "instruction": "You are given a statement written in Marathi. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .",
        "input": "Statement: \u091c\u0941\u0932\u0948-\u0911\u0917\u0938\u094d\u091f \u0968\u0966\u0966\u096f \u092e\u0927\u094d\u092f\u0947 \u0911\u0938\u094d\u091f\u094d\u0930\u0947\u0932\u093f\u092f\u093e\u0924 \u0939\u094b\u0923\u093e\u0930\u094d\u200d\u092f\u093e \u091a\u093e\u0930 \u0938\u0902\u0918\u093e\u0902\u091a\u094d\u092f\u093e \u0909\u0926\u092f\u094b\u0928\u094d\u092e\u0941\u0916 \u0916\u0947\u0933\u093e\u0921\u0942\u0902\u091a\u094d\u092f\u093e \u0938\u094d\u092a\u0930\u094d\u0927\u0947\u0938\u093e\u0920\u0940 \u0915\u094b\u0939\u0932\u0940\u091a\u0940 \u0928\u093f\u0935\u0921 \u091d\u093e\u0932\u0940. \u0924\u094d\u092f\u093e\u0928\u0947 \u092d\u093e\u0930\u0924 \u0909\u0926\u092f\u094b\u0928\u094d\u092e\u0941\u0916 \u0916\u0947\u0933\u093e\u0921\u0942\u0902\u091a\u094d\u092f\u093e \u0938\u0902\u0918\u093e\u0938\u093e\u0920\u0940 \u092f\u093e \u0938\u094d\u092a\u0930\u094d\u0927\u0947\u0924 \u0938\u0932\u093e\u092e\u0940\u0935\u0940\u0930\u093e\u091a\u0940 \u092d\u0942\u092e\u093f\u0915\u093e \u092c\u091c\u093e\u0935\u0932\u0940. \u0938\u0926\u0930 \u0938\u094d\u092a\u0930\u094d\u0927\u0947\u0924 \u0924\u094d\u092f\u093e\u0928\u0947 \u0938\u093e\u0924 \u0938\u093e\u092e\u0928\u094d\u092f\u093e\u0902\u0924 \u096c\u096c.\u0969\u0969 \u091a\u094d\u092f\u093e \u0938\u0930\u093e\u0938\u0930\u0940\u0928\u0947 \u0938\u094d\u092a\u0930\u094d\u0927\u0947\u0924 \u0938\u0930\u094d\u0935\u093e\u0927\u093f\u0915 \u0969\u096f\u096e \u0927\u093e\u0935\u093e \u0915\u0947\u0932\u094d\u092f\u093e. \u0924\u094d\u092f\u093e\u0928\u0947 <MASK> \u092f\u0947\u0925\u0940\u0932 \u0905\u0902\u0924\u093f\u092e \u0938\u093e\u092e\u0928\u094d\u092f\u093e\u0924 \u0926\u0915\u094d\u0937\u093f\u0923 \u0906\u092b\u094d\u0930\u093f\u0915\u0947\u091a\u094d\u092f\u093e \u0938\u0902\u0918\u093e\u0935\u093f\u0930\u0941\u0926\u094d\u0927 \u0967\u0966\u0968 \u091a\u0947\u0902\u0921\u0942\u0924 \u0967\u0966\u096a \u0927\u093e\u0935\u093e \u0915\u0947\u0932\u094d\u092f\u093e. \u092d\u093e\u0930\u0924\u093e\u0928\u0947 \u0924\u094b \u0938\u093e\u092e\u0928\u093e \u0967\u096d \u0927\u093e\u0935\u093e\u0902\u0928\u0940 \u091c\u093f\u0902\u0915\u0942\u0928 \u0935\u093f\u091c\u0947\u0924\u0947\u092a\u0926 \u092a\u091f\u0915\u093e\u0935\u0932\u0947.  \u0938\u094d\u092a\u0930\u094d\u0927\u0947\u091a\u094d\u092f\u093e \u0936\u0947\u0935\u091f\u0940 \u0930\u093e\u0937\u094d\u091f\u094d\u0930\u0940\u092f \u0928\u093f\u0935\u0921 \u0938\u092e\u093f\u0924\u0940\u091a\u0947 \u0905\u0927\u094d\u092f\u0915\u094d\u0937 \u0915\u0943\u0937\u094d\u0923\u092e\u094d\u092e\u093e\u091a\u093e\u0930\u0940 \u0936\u094d\u0930\u0940\u0915\u093e\u0902\u0924 \u0915\u094b\u0939\u0932\u0940\u091a\u094d\u092f\u093e \u0915\u093e\u092e\u0917\u093f\u0930\u0940\u0935\u0930 \u0916\u0942\u0937 \u0939\u094b\u090a\u0928 \u092e\u094d\u0939\u0923\u093e\u0932\u0947, \"\u092e\u0932\u093e \u0938\u093e\u0902\u0917\u093e\u0935\u0938\u0902 \u0935\u093e\u091f\u0924\u0902\u092f, \u0938\u0932\u093e\u092e\u0940\u0935\u0940\u0930 \u0935\u093f\u0930\u093e\u091f \u0915\u094b\u0939\u0932\u0940 \u0916\u0942\u092a\u091a \u091b\u093e\u0928 \u0916\u0947\u0933\u0932\u093e. \u0924\u094d\u092f\u093e\u0928\u0947 \u0916\u0947\u0933\u0932\u0947\u0932\u094d\u092f\u093e \u0915\u093e\u0939\u0940 \u092b\u091f\u0915\u0947\u091a \u0924\u094d\u092f\u093e\u091a\u0940 \u0915\u094d\u0937\u092e\u0924\u093e \u0938\u093f\u0926\u094d\u0927 \u0915\u0930\u0924\u093e\u0924.\" \u0915\u094b\u0939\u0932\u0940\u091a\u094d\u092f\u093e \u092e\u0924\u0947 \u0939\u0940 \u0938\u094d\u092a\u0930\u094d\u0927\u093e \u092e\u094d\u0939\u0923\u091c\u0947 \u0924\u094d\u092f\u093e\u091a\u094d\u092f\u093e \u0915\u093e\u0930\u0915\u093f\u200d\u0930\u094d\u0926\u0940\u0932\u093e \u0915\u0932\u093e\u091f\u0923\u0940 \u0926\u0947\u0923\u093e\u0930\u093e \u0915\u094d\u0937\u0923 \u0939\u094b\u0924\u093e.\n\n Option A: \u091f\u093e\u092f\u091f\u0928\n\n Option B: \u0915\u093f\u0902\u0917\u0938\u094d\u091f\u0928\n\n Option C: \u092c\u094d\u0930\u093f\u0938\u094d\u092c\u0947\u0928\n\n Option D: \u0915\u093f\u0932\u094d\u0932\u093e",
        "output": "\u092c\u094d\u0930\u093f\u0938\u094d\u092c\u0947\u0928",
        "category": "Fill in The Blank 1566.json"
    },
    {
        "instruction": "You are given a statement written in Panjabi. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .",
        "input": "Statement: \u0a08\u0a26\u0a40 \u0a05\u0a2e\u0a40\u0a28 \u0a26\u0a3e\u0a26\u0a3e\u00a0(/\u02c8i\u02d0di \u0251\u02d0\u02c8mi\u02d0n/; \u20091923\u201328\u00a016 \u0a05\u0a17\u0a38\u0a24 2003)\u00a01971 \u0a24\u0a4b\u0a02 1979 \u0a24\u0a71\u0a15 \u0a30\u0a3e\u0a1c \u0a15\u0a30\u0a28 \u0a35\u0a3e\u0a32\u0a3e <MASK> \u0a26\u0a3e \u0a2b\u0a4c\u0a1c\u0a40 \u0a28\u0a47\u0a24\u0a3e \u0a05\u0a24\u0a47 \u0a30\u0a3e\u0a38\u0a3c\u0a1f\u0a30\u0a2a\u0a24\u0a40 \u0a38\u0a40\u0964 1946 \u0a35\u0a3f\u0a71\u0a1a \u0a05\u0a2e\u0a40\u0a28 \u0a2c\u0a30\u0a24\u0a3e\u0a28\u0a35\u0a40 \u0a2c\u0a38\u0a24\u0a40\u0a35\u0a3e\u0a26\u0a40 \u0a30\u0a48\u0a1c\u0a3f\u0a2e\u0a47\u0a02\u0a1f \u0a15\u0a3f\u0a70\u0a17\u0a38 \u0a05\u0a2b\u0a30\u0a40\u0a15\u0a40 \u0a30\u0a3e\u0a07\u0a2b\u0a32\u0a38 \u0a35\u0a3f\u0a71\u0a1a \u0a38\u0a3c\u0a3e\u0a2e\u0a3f\u0a32 \u0a39\u0a4b \u0a17\u0a3f\u0a06 \u0a05\u0a24\u0a47 \u0a1c\u0a28\u0a35\u0a30\u0a40 1971 \u0a26\u0a47 \u0a2b\u0a4c\u0a1c\u0a40 \u0a24\u0a16\u0a24\u0a3e\u0a2a\u0a32\u0a1f \u0a26\u0a41\u0a06\u0a30\u0a3e \u0a2e\u0a3f\u0a32\u0a1f\u0a28 \u0a13\u0a2c\u0a4b\u0a1f\u0a47 \u0a28\u0a42\u0a70 \u0a2a\u0a26 \u0a24\u0a4b\u0a02 \u0a39\u0a1f\u0a3e\u0a09\u0a23 \u0a2a\u0a3f\u0a71\u0a1b\u0a4b\u0a02 \u0a2f\u0a41\u0a17\u0a3e\u0a02\u0a21\u0a3e \u0a26\u0a40 \u0a2b\u0a4c\u0a1c \u0a35\u0a3f\u0a71\u0a1a \u0a13\u0a5c\u0a15 \u0a2e\u0a47\u0a1c\u0a30 \u0a1c\u0a28\u0a30\u0a32 \u0a05\u0a24\u0a47 \u0a15\u0a2e\u0a3e\u0a02\u0a21\u0a30 \u0a26\u0a3e \u0a2a\u0a26 \u0a39\u0a3e\u0a38\u0a32 \u0a15\u0a40\u0a24\u0a3e\u0964 \u0a2c\u0a3e\u0a05\u0a26 \u0a35\u0a3f\u0a71\u0a1a \u0a26\u0a47\u0a38\u0a3c \u0a26\u0a47 \u0a2a\u0a4d\u0a30\u0a2e\u0a41\u0a71\u0a16 \u0a2a\u0a26 \u0a09\u0a71\u0a24\u0a47 \u0a35\u0a3f\u0a30\u0a3e\u0a1c\u0a2e\u0a3e\u0a28 \u0a30\u0a39\u0a3f\u0a70\u0a26\u0a47 \u0a39\u0a4b\u0a0f \u0a09\u0a38\u0a28\u0a47 \u0a06\u0a2a \u0a28\u0a42\u0a70 \u0a2b\u0a40\u0a32\u0a21 \u0a2e\u0a3e\u0a30\u0a38\u0a3c\u0a32 \u0a26\u0a47 \u0a30\u0a42\u0a2a \u0a35\u0a3f\u0a71\u0a1a \u0a24\u0a30\u0a71\u0a15\u0a40 \u0a15\u0a30 \u0a32\u0a08\u0964\n\n Option A: \u0a2f\u0a41\u0a17\u0a3e\u0a02\u0a21\u0a3e\n\n Option B: \u0a24\u0a28\u0a1c\u0a3c\u0a3e\u0a28\u0a40\u0a06\n\n Option C: \u0a32\u0a40\u0a2c\u0a40\u0a06\n\n Option D: \u0a09\u0a2c\u0a41\u0a28\u0a1f\u0a42",
        "output": "\u0a2f\u0a41\u0a17\u0a3e\u0a02\u0a21\u0a3e",
        "category": "Fill in The Blank 1568.json"
    },
    {
        "instruction": "You are given a statement written in Tamil. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .",
        "input": "Statement: \u0ba4\u0bae\u0bbf\u0bb4\u0bc0\u0bb4 \u0bb5\u0bbf\u0b9f\u0bc1\u0ba4\u0bb2\u0bc8\u0baa\u0bcd\u0baa\u0bc1\u0bb2\u0bbf\u0b95\u0bb3\u0bbf\u0ba9\u0bcd \u0baa\u0b9f\u0bc8\u0ba4\u0bcd\u0ba4\u0bc1\u0bb1\u0bc8\u0baa\u0bcd \u0baa\u0bc7\u0b9a\u0bcd\u0b9a\u0bbe\u0bb3\u0bb0\u0bcd \u0b87\u0bb0\u0bbe\u0b9a\u0bc8\u0baf\u0bbe \u0b87\u0bb3\u0ba8\u0bcd\u0ba4\u0bbf\u0bb0\u0bc8\u0baf\u0ba9\u0bcd \u0b87\u0bb5\u0bcd\u0bb5\u0bbf\u0bb0\u0bc1\u0bb5\u0bb4\u0bbf\u0ba4\u0bcd \u0ba4\u0bbe\u0b95\u0bcd\u0b95\u0bc1\u0ba4\u0bb2\u0bbf\u0bb2\u0bcd \u0b87\u0bb2\u0b99\u0bcd\u0b95\u0bc8 \u0bb5\u0bbf\u0bae\u0bbe\u0ba9\u0baa\u0bcd\u0baa\u0b9f\u0bc8\u0b95\u0bcd\u0b95\u0bc1\u0b9a\u0bcd \u0b9a\u0bca\u0ba8\u0bcd\u0ba4\u0bae\u0bbe\u0ba9 8 \u0bb5\u0bbf\u0bae\u0bbe\u0ba9\u0b99\u0bcd\u0b95\u0bb3\u0bcd \u0ba4\u0bbe\u0b95\u0bcd\u0b95\u0bbf\u0baf\u0bb4\u0bbf\u0b95\u0bcd\u0b95\u0baa\u0bcd\u0baa\u0b9f\u0bcd\u0b9f\u0ba4\u0bbe\u0b95 <MASK>\u0b95\u0bcd\u0b95\u0bc1 \u0b85\u0bb3\u0bbf\u0ba4\u0bcd\u0ba4 \u0b9a\u0bc6\u0bb5\u0bcd\u0bb5\u0bbf\u0baf\u0bbf\u0bb2\u0bcd \u0b95\u0bc1\u0bb1\u0bbf\u0baa\u0bcd\u0baa\u0bbf\u0b9f\u0bcd\u0b9f\u0bbe\u0bb0\u0bcd. \u0baa\u0baf\u0bbf\u0bb1\u0bcd\u0b9a\u0bbf \u0bb5\u0bbf\u0bae\u0bbe\u0ba9\u0bae\u0bcd \u0b92\u0ba9\u0bcd\u0bb1\u0bc1, \u0b8e\u0bae\u0bcd.\u0b90. 24 \u0bb5\u0b95\u0bc8 \u0b89\u0bb2\u0b99\u0bcd\u0b95\u0bc1 \u0bb5\u0bbe\u0ba9\u0bc2\u0bb0\u0bcd\u0ba4\u0bbf\u0b95\u0bb3\u0bcd \u0b87\u0bb0\u0ba3\u0bcd\u0b9f\u0bc1, \u0baa\u0bbf.\u0b9f\u0bbf. 6 \u0bb5\u0b95\u0bc8 \u0bb5\u0bbf\u0bae\u0bbe\u0ba9\u0bae\u0bcd \u0b92\u0ba9\u0bcd\u0bb1\u0bc1, \u0baa\u0bc6\u0bb2\u0bcd 212 \u0bb5\u0b95\u0bc8 \u0b89\u0bb2\u0b99\u0bcd\u0b95\u0bc1 \u0bb5\u0bbe\u0ba9\u0bc2\u0bb0\u0bcd\u0ba4\u0bbf \u0b92\u0ba9\u0bcd\u0bb1\u0bc1, \u0b89\u0bb3\u0bb5\u0bc1 \u0bb5\u0bbf\u0bae\u0bbe\u0ba9\u0bae\u0bcd \u0b92\u0ba9\u0bcd\u0bb1\u0bc1, \u0b9a\u0bbf.\u0b9f\u0bbf.\u0b8e\u0b9a\u0bcd. 748 \u0bb0\u0b95 \u0bb5\u0bbf\u0bae\u0bbe\u0ba9\u0bae\u0bcd \u0b92\u0ba9\u0bcd\u0bb1\u0bc1, \u0bae\u0bb1\u0bcd\u0bb1\u0bc1\u0bae\u0bcd \u0bb5\u0b95\u0bc8 \u0b85\u0bb1\u0bbf\u0baf\u0baa\u0bcd\u0baa\u0b9f\u0bbe\u0ba4 \u0b87\u0ba9\u0bcd\u0ba9\u0bc1\u0bae\u0bca\u0bb0\u0bc1 \u0bb5\u0bbf\u0bae\u0bbe\u0ba9\u0bae\u0bcd \u0b92\u0ba9\u0bcd\u0bb1\u0bc1\u0bae\u0bcd \u0ba4\u0bbe\u0b95\u0bcd\u0b95\u0bbf\u0baf\u0bb4\u0bbf\u0b95\u0bcd\u0b95\u0baa\u0bcd\u0baa\u0b9f\u0bcd\u0b9f\u0ba4\u0bbe\u0b95 \u0bb5\u0bbf\u0b9f\u0bc1\u0ba4\u0bb2\u0bc8\u0baa\u0bcd \u0baa\u0bc1\u0bb2\u0bbf\u0b95\u0bb3\u0bcd \u0b95\u0bcb\u0bb0\u0bbf\u0ba9\u0bbe\u0bb0\u0bcd\u0b95\u0bb3\u0bcd.\n\n Option A: \u0b87\u0bb2\u0b99\u0bcd\u0b95\u0bc8\u0baf\u0bc8\n\n Option B: \u0b87\u0bb2\u0b99\u0bcd\u0b95\u0bc8\n\n Option C: \u0b87\u0ba8\u0bcd\u0ba4\u0bbf\u0baf\u0baa\u0bcd\n\n Option D: \u0bb5\u0bc0\u0bb0\u0b95\u0bc7\u0b9a\u0bb0\u0bbf",
        "output": "\u0bb5\u0bc0\u0bb0\u0b95\u0bc7\u0b9a\u0bb0\u0bbf",
        "category": "Fill in The Blank 1569.json"
    },
    {
        "instruction": "You are given a statement written in Telugu. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .",
        "input": "Statement: \u0c17\u0c4d\u0c30\u0c3e\u0c2e\u0c02\u0c32\u0c4b \u0c12\u0c15 \u0c2a\u0c4d\u0c30\u0c48\u0c35\u0c47\u0c1f\u0c41 \u0c2c\u0c3e\u0c32\u0c2c\u0c21\u0c3f \u0c09\u0c02\u0c26\u0c3f. \u0c2a\u0c4d\u0c30\u0c2d\u0c41\u0c24\u0c4d\u0c35 \u0c2a\u0c4d\u0c30\u0c3e\u0c25\u0c2e\u0c3f\u0c15 \u0c2a\u0c3e\u0c20\u0c36\u0c3e\u0c32\u0c32\u0c41 \u0c30\u0c46\u0c02\u0c21\u0c41, \u0c2a\u0c4d\u0c30\u0c48\u0c35\u0c47\u0c1f\u0c41 \u0c2a\u0c4d\u0c30\u0c3e\u0c25\u0c2e\u0c3f\u0c15 \u0c2a\u0c3e\u0c20\u0c36\u0c3e\u0c32 \u0c12\u0c15\u0c1f\u0c3f , \u0c2a\u0c4d\u0c30\u0c2d\u0c41\u0c24\u0c4d\u0c35 \u0c2a\u0c4d\u0c30\u0c3e\u0c25\u0c2e\u0c3f\u0c15\u0c4b\u0c28\u0c4d\u0c28\u0c24 \u0c2a\u0c3e\u0c20\u0c36\u0c3e\u0c32\u0c32\u0c41 \u0c30\u0c46\u0c02\u0c21\u0c41 , \u0c2a\u0c4d\u0c30\u0c48\u0c35\u0c47\u0c1f\u0c41 \u0c2a\u0c4d\u0c30\u0c3e\u0c25\u0c2e\u0c3f\u0c15\u0c4b\u0c28\u0c4d\u0c28\u0c24 \u0c2a\u0c3e\u0c20\u0c36\u0c3e\u0c32 \u0c12\u0c15\u0c1f\u0c3f, \u0c2a\u0c4d\u0c30\u0c2d\u0c41\u0c24\u0c4d\u0c35 \u0c2e\u0c3e\u0c27\u0c4d\u0c2f\u0c2e\u0c3f\u0c15 \u0c2a\u0c3e\u0c20\u0c36\u0c3e\u0c32\u0c32\u0c41 \u0c30\u0c46\u0c02\u0c21\u0c41 \u0c09\u0c28\u0c4d\u0c28\u0c3e\u0c2f\u0c3f. \u0c12\u0c15 \u0c2a\u0c4d\u0c30\u0c2d\u0c41\u0c24\u0c4d\u0c35 \u0c1c\u0c42\u0c28\u0c3f\u0c2f\u0c30\u0c4d \u0c15\u0c33\u0c3e\u0c36\u0c3e\u0c32 \u0c09\u0c02\u0c26\u0c3f.\u0c38\u0c2e\u0c40\u0c2a \u0c2a\u0c4d\u0c30\u0c2d\u0c41\u0c24\u0c4d\u0c35 \u0c06\u0c30\u0c4d\u0c1f\u0c4d\u0c38\u0c4d / \u0c38\u0c48\u0c28\u0c4d\u0c38\u0c4d \u0c21\u0c3f\u0c17\u0c4d\u0c30\u0c40 \u0c15\u0c33\u0c3e\u0c36\u0c3e\u0c32 \u0c28\u0c30\u0c4d\u0c38\u0c40\u0c2a\u0c1f\u0c4d\u0c28\u0c02\u0c32\u0c4b\u0c28\u0c41, \u0c07\u0c02\u0c1c\u0c28\u0c40\u0c30\u0c3f\u0c02\u0c17\u0c4d \u0c15\u0c33\u0c3e\u0c36\u0c3e\u0c32 <MASK>\u0c32\u0c4b\u0c28\u0c42 \u0c09\u0c28\u0c4d\u0c28\u0c3e\u0c2f\u0c3f. \u0c38\u0c2e\u0c40\u0c2a \u0c35\u0c48\u0c26\u0c4d\u0c2f \u0c15\u0c33\u0c3e\u0c36\u0c3e\u0c32, \u0c2e\u0c47\u0c28\u0c47\u0c1c\u0c3f\u0c2e\u0c46\u0c02\u0c1f\u0c41 \u0c15\u0c33\u0c3e\u0c36\u0c3e\u0c32 \u0c35\u0c3f\u0c36\u0c3e\u0c16\u0c2a\u0c1f\u0c4d\u0c28\u0c02\u0c32\u0c4b\u0c28\u0c41, \u0c2a\u0c3e\u0c32\u0c40\u0c1f\u0c46\u0c15\u0c4d\u0c28\u0c3f\u0c15\u0c4d \u0c28\u0c30\u0c4d\u0c38\u0c40\u0c2a\u0c1f\u0c4d\u0c28\u0c02\u0c32\u0c4b\u0c28\u0c42 \u0c09\u0c28\u0c4d\u0c28\u0c3e\u0c2f\u0c3f. \u0c38\u0c2e\u0c40\u0c2a \u0c35\u0c43\u0c24\u0c4d\u0c24\u0c3f \u0c35\u0c3f\u0c26\u0c4d\u0c2f\u0c3e \u0c36\u0c3f\u0c15\u0c4d\u0c37\u0c23 \u0c2a\u0c3e\u0c20\u0c36\u0c3e\u0c32 \u0c2a\u0c46\u0c26\u0c2c\u0c4a\u0c21\u0c4d\u0c21\u0c47\u0c2a\u0c32\u0c4d\u0c32\u0c3f\u0c32\u0c4b\u0c28\u0c41, \u0c05\u0c28\u0c3f\u0c2f\u0c24 \u0c35\u0c3f\u0c26\u0c4d\u0c2f\u0c3e \u0c15\u0c47\u0c02\u0c26\u0c4d\u0c30\u0c02 \u0c05\u0c28\u0c15\u0c3e\u0c2a\u0c32\u0c4d\u0c32\u0c3f\u0c32\u0c4b\u0c28\u0c41, \u0c26\u0c3f\u0c35\u0c4d\u0c2f\u0c3e\u0c02\u0c17\u0c41\u0c32 \u0c2a\u0c4d\u0c30\u0c24\u0c4d\u0c2f\u0c47\u0c15 \u0c2a\u0c3e\u0c20\u0c36\u0c3e\u0c32 \u0c35\u0c3f\u0c36\u0c3e\u0c16\u0c2a\u0c1f\u0c4d\u0c28\u0c02 \u0c32\u0c4b\u0c28\u0c42 \u0c09\u0c28\u0c4d\u0c28\u0c3e\u0c2f\u0c3f.\n\n Option A: \u0c2e\u0c3e\u0c15\u0c35\u0c30\u0c2a\u0c3e\u0c32\u0c46\u0c02\n\n Option B: \u0c28\u0c30\u0c4d\u0c38\u0c40\u0c2a\u0c1f\u0c4d\u0c28\u0c02\n\n Option C: \u0c05\u0c28\u0c15\u0c3e\u0c2a\u0c32\u0c4d\u0c32\u0c3f\n\n Option D: \u0c2e\u0c3e\u0c27\u0c35\u0c2e\u0c3e\u0c32",
        "output": "\u0c2e\u0c3e\u0c15\u0c35\u0c30\u0c2a\u0c3e\u0c32\u0c46\u0c02",
        "category": "Fill in The Blank 1570.json"
    },
    {
        "instruction": "You are given a password and you need to generate the number of steps required to convert the given password to a strong password. A password is considered strong if (a) it has at least 6 characters and at most 20 characters; (b) it contains at least one lowercase letter and one uppercase letter, and at least one digit; (c) it does not contain three repeating characters in a row. In one step you can: (1) Insert one character to password, (2) delete one character from password, or (3) replace one character of password with another character.",
        "input": "password = Z0IFbxOeQaa.JR9ghwoXEj86O6d42KqOdf",
        "output": "14",
        "category": "Text to Code 1572.json"
    },
    {
        "instruction": "In this task, you're given a four sentences of story written in natural language. Your job is to complete end part of the story by predicting appropriate last sentence which is coherent with the given sentences.",
        "input": "Sentence1: Will wanted to quit smoking. Sentence2: It gave him a bad cough. Sentence3: He bought a nicotine patch at the store. Sentence4: Used the patch for a month.",
        "output": "He finally quit smoking.",
        "category": "Text Completion 164.json"
    },
    {
        "instruction": "In this task, you are given two simple actions (associated with \"A\", \"B\"). You must identify which action is considered less ethical. Do not generate anything else apart from one of the following characters: 'A', 'B'.",
        "input": "(A) snapping at my friend for calling my major and life easy\n(B) saying yes when my bestfriend asked me to cheat on her boyfriend with her",
        "output": "B",
        "category": "Ethics Classification 175.json"
    },
    {
        "instruction": "Read the given text and if it has abusive content then indicate via \"yes\". Otherwise indicate via\"no\". \nWe consider the content to be abusive if it contains any of the following instances: (1) Identity Directed Abuse (e.g., Content which contains a negative statement made against an identity. An identity is a social category that relates to a fundamental aspect of individuals community, socio-demographics, position or self-representation) (2) Affiliation Directed Abuse (e.g., Content which express negativity against an affiliation. We define affiliation as a (more or less) voluntary association with a collective. Affiliations include but are not limited to: memberships (e.g. Trade unions), party memberships (e.g. Republicans), political affiliations (e.g. Right-wing people) and occupations (e.g. Doctors).) (3) Person Directed Abuse (e.g., Content which directs negativity against an identifiable person, who is either part of the conversation thread or is named. Person-directed abuse includes serious character based attacks, such as accusing the person of lying, as well as aggression, insults and menacing language.) and (4) Counter Speech (e.g., Content which challenges, condemns or calls out the abusive language of others.). Note that URLs in the text have been replaced with [Link].",
        "input": "Police: Smollett suspected of lying about attack",
        "output": "no",
        "category": "Toxic Language Detection 197.json"
    },
    {
        "instruction": "You are given a sentence in English. Your job is to translate the English sentence into Galician.",
        "input": "We know that actual human consciousness has something more than that.",
        "output": "sabemos que a consciencia humana ten algo m\u00e1is que iso,",
        "category": "Translation 198.json"
    },
    {
        "instruction": "You are given a sentence in English. Your job is to translate the English sentence into Italian.",
        "input": "(Laughter) In this case, this is a Philly cheesesteak hoagie that it's grabbing out of thin air. (Laughter)",
        "output": "(Risate) In questo caso un panino al formaggio che afferra in volo. (Risate)",
        "category": "Translation 199.json"
    },
    {
        "instruction": "You are given a sentence in English. Your job is to translate the English sentence into Polish.",
        "input": "Child: Oh my God! How did you do that?",
        "output": "Dziecko: O Bo\u017ce! Jak pan to zrobi\u0142?",
        "category": "Translation 200.json"
    },
    {
        "instruction": "You are given a sentence in English. Your job is to translate the English sentence into Persian.",
        "input": "What you're looking at here is an X-ray of the column that you just saw, viewed from the top.",
        "output": "\u0622\u0646\u0686\u0647 \u0634\u0645\u0627 \u062f\u0631 \u0627\u06cc\u0646\u062c\u0627 \u0645\u0644\u0627\u062d\u0638\u0647 \u0645\u06cc \u06a9\u0646\u06cc\u062f \u060c \u062a\u0635\u0648\u06cc\u0631 \u0627\u0634\u0639\u0647 \u0627\u06cc\u06a9\u0633 \u0627\u0632 \u0633\u062a\u0648\u0646\u06cc \u0627\u0633\u062a \u06a9\u0647 \u0647\u0645 \u0627\u06a9\u0646\u0648\u0646 \u0627\u0632 \u062c\u0647\u062a \u0628\u0627\u0644\u0627 \u0645\u0634\u0627\u0647\u062f\u0647 \u06a9\u0631\u062f\u06cc\u062f.",
        "category": "Translation 201.json"
    },
    {
        "instruction": "You are given a sentence in English. Your job is to translate the English sentence into Portugese.",
        "input": "So we can then ask for Denisovans the same things as for the Neanderthals: Did they mix with ancestors of present day people?",
        "output": "Podemos ent\u00e3o perguntar para os Denisovanos o que pergunt\u00e1mos para os Neandertais: Ser\u00e1 que se misturaram com antepassados das pessoas actuais?",
        "category": "Translation 202.json"
    },
    {
        "instruction": "You are given a sentence in Japanese. Your job is to translate the Japanese sentence into Galician.",
        "input": "\u3067\u306f\u9032\u3080\u524d\u306b\u5c11\u3057\u7c21\u5358\u306b\u8aac\u660e\u3057\u307e\u3059 RKCP\u304c\u3069\u3046\u52d5\u304f\u306e\u304b",
        "output": "Agora, antes de que sigamos, deix\u00e1deme describir moi r\u00e1pida e brevemente, c\u00f3mo funciona RKCP.",
        "category": "Translation 203.json"
    },
    {
        "instruction": "You are given a sentence in Japanese. Your job is to translate the Japanese sentence into Italian.",
        "input": "\u3042\u308a\u304c\u3068\u3046\u3054\u3056\u3044\u307e\u3057\u305f \uff08 \u62cd\u624b \uff09",
        "output": "Grazie. (Applausi)",
        "category": "Translation 204.json"
    },
    {
        "instruction": "You are given a sentence in Japanese. Your job is to translate the Japanese sentence into Polish.",
        "input": "\u30c7\u30a4\u30d3\u30c3\u30c9 \uff1a \u8a71\u3092\u3057\u3066\u308b\u3093\u3060",
        "output": "Rozmawiam w tej chwili.",
        "category": "Translation 205.json"
    },
    {
        "instruction": "You are given a sentence in Japanese. Your job is to translate the Japanese sentence into Farsi.",
        "input": "\u30ca\u30d3\u30b8\u30a7\u30cb\u30af\u30b9\u3001 DNA\u30c0\u30a4\u30ec\u30af\u30c8\u3001 23 & ME\u306a\u3069\u306e\u3088\u3046\u306a\u907a\u4f1d\u5b50\u30d7\u30ed\u30d5\u30a1\u30a4\u30eb\u3092\u63d0\u4f9b\u3059\u308b\u4f1a\u793e\u306b\u5bfe\u3057\u3001 \u201d \u3048\u3063\u3001\u305d\u308c\u3067\u4f55\u304c\u3067\u304d\u308b\u3063\u3066\u3044\u3046\u306e \uff1f \u201d \u3068\u601d\u3046\u4eba\u3082\u3044\u307e\u3059\u3067\u3059\u306e\u3067\u3001\u79c1\u9054\u306e\u907a\u4f1d\u5b50\u306f\u904b\u547d\u3067\u6c7a\u307e\u3063\u3066\u3044\u308b\u3082\u306e\u3067\u306f\u306a\u306e\u3067\u3059\u3002\u3082\u3057\u3001\u751f\u6d3b\u7fd2\u6163\u3092\u5909\u3048\u308b\u3068\u3001\u305d\u306e\u5909\u5316\u306f\u5358\u306a\u308b\u7fd2\u6163\u3067\u3059\u304c\u3001\u3082\u3057\u3001\u3053\u308c\u307e\u3067\u306e\u7fd2\u6163\u3088\u308a\u3082\u5927\u3005\u7684\u306b\u751f\u6d3b\u7fd2\u6163\u3092\u5909\u3048\u308b\u3068\u3001\u907a\u4f1d\u5b50\u306e\u767a\u73fe\u3092\u5b9f\u969b\u306b\u5909\u3048\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3059",
        "output": "\u0648 \u0634\u0631\u06a9\u062a \u200c \u0647\u0627\u06cc\u06cc \u0686\u0648\u0646 \u0646\u064e\u0648\u06cc\u062c\u0646\u06cc\u06a9\u0633 \u0648 \u062f\u06cc \u0627\u0650\u0646 \u0627\u0650\u06cc \u062f\u06cc\u0631\u06a9\u062a \u0648 \u06f2\u06f3\u0627\u0646\u062f\u0645\u06cc \u060c \u06a9\u0647 \u0628\u0647 \u0634\u0645\u0627 \u067e\u0631\u0648\u0641\u0627\u06cc\u0644 \u200c \u0647\u0627\u06cc \u0698\u0646\u062a\u06cc\u06a9\u06cc \u0645\u06cc \u200c \u062f\u0647\u0646\u062f \u060c \u0628\u0647 \u0628\u0631\u062e\u06cc \u0627\u06cc\u0646 \u0627\u062d\u0633\u0627\u0633 \u0631\u0627 \u0627\u0644\u0642\u0627 \u0645\u06cc \u200c \u06a9\u0646\u0646\u062f \u06a9\u0647 \u060c \u00ab \u0639\u062c\u0628 \u060c \u0645\u0646 \u0686\u0647 \u06a9\u0627\u0631 \u0645\u06cc \u200c \u062a\u0648\u0627\u0646\u0645 \u0628\u06a9\u0646\u0645 \u061f \u00bb \u062e\u0648\u0628 \u060c \u0698\u0646 \u200c \u0647\u0627\u06cc \u0645\u0627 \u0633\u0631\u0646\u0648\u0634\u062a \u0645\u0627 \u0646\u06cc\u0633\u062a\u0646\u062f \u060c \u0648 \u0627\u06af\u0631 \u0645\u0627 \u0627\u06cc\u0646 \u062a\u063a\u06cc\u06cc\u0631\u0627\u062a \u0631\u0627 \u0627\u0646\u062c\u0627\u0645 \u0628\u062f\u0647\u06cc\u0645 \u2014 \u0622\u0646\u0647\u0627 \u06cc\u06a9 \u0686\u06cc\u0632 \u0627\u0633\u062a\u0639\u062f\u0627\u062f\u06cc \u0627\u0646\u062f \u060c \u0648\u0644\u06cc \u0627\u06af\u0631 \u0645\u0627 \u062a\u063a\u06cc\u06cc\u0631\u0627\u062a \u0628\u0632\u0631\u06af\u062a\u0631\u06cc \u0628\u062f\u0647\u06cc\u0645 \u0627\u0632 \u062a\u063a\u06cc\u06cc\u0631\u06cc \u06a9\u0647 \u062f\u0631 \u063a\u06cc\u0631 \u0627\u06cc\u0646 \u0635\u0648\u0631\u062a \u0645\u06cc \u200c \u062f\u0627\u062f\u06cc\u0645 \u0645\u0627 \u062f\u0631 \u0648\u0627\u0642\u0639 \u0645\u06cc \u200c \u062a\u0648\u0627\u0646\u06cc\u0645 \u0686\u06af\u0648\u0646\u06af\u06cc \u0638\u0647\u0648\u0631 \u0698\u0646 \u200c \u0647\u0627\u06cc\u0645\u0627\u0646 \u0631\u0627 \u0639\u0648\u0636 \u06a9\u0646\u06cc\u0645.",
        "category": "Translation 206.json"
    },
    {
        "instruction": "You are given a sentence in Japanese. Your job is to translate the Japanese sentence into Portugese.",
        "input": "\u305d\u308c\u306b\u512a\u308c\u3066\u3044\u307e\u3059",
        "output": "E claro, a matem\u00e1tica \u00e9 muito poderosa a fazer isso.",
        "category": "Translation 207.json"
    },
    {
        "instruction": "You are given a sentence in Spanish. Your job is to translate the Spanish sentence into Galician.",
        "input": "\u00bfY si mi madre nos hubiera contado que la familia de Fide era pobre y trabajadora?",
        "output": "\u00bfQue pasar\u00eda se a mi\u00f1a nai nos contara que a familia de Fide era pobre e traballadora?",
        "category": "Translation 209.json"
    },
    {
        "instruction": "You are given a sentence in Spanish. Your job is to translate the Spanish sentence into Italian.",
        "input": "Y pienso en lo que eso nos hace psicol\u00f3gicamente, crea una ecuaci\u00f3n.",
        "output": "E penso che \u2014 che questa idea del tempo ci influenzi psicologicamente, che \u2014 che crei un'equazione.",
        "category": "Translation 210.json"
    },
    {
        "instruction": "You are given a sentence in Spanish. Your job is to translate the Spanish sentence into Polish.",
        "input": "\"\u00bfPuedo llevarla al hospital?, \u00bfPuedo conseguirle un doctor?\"",
        "output": "Czy mo\u017ce zawie\u017a\u0107 j\u0105 do szpitala, zap\u0142aci\u0107 za lekarza?",
        "category": "Translation 211.json"
    },
    {
        "instruction": "You are given a sentence in Spanish. Your job is to translate the Spanish sentence into Farsi.",
        "input": "Tambi\u00e9n es conocida m\u00e1s benignamente como \"\" seta de miel \"\" u \"\" hongo gigantesco \"\" porque resulta ser tambi\u00e9n uno de los organismos m\u00e1s grandes del mundo.",
        "output": "\u0627\u06cc\u0646 \u0645\u0634\u0647\u0648\u0631 \u0628\u0647 \u0642\u0627\u0631\u062c \u0639\u0633\u0644\u06cc \u0648 \u06cc\u0627 \"\" \u0642\u0627\u0631\u0686 \u0647\u0627\u0645\u0648\u0646\u06af\u0648\u0633 \"\" \u0627\u0633\u062a \u0632\u06cc\u0631\u0627 \u0627\u062a\u0641\u0627\u0642 \u0645\u06cc \u0627\u0641\u062a\u062f \u06a9\u0647 \u06cc\u06a9\u06cc \u0627\u0632 \u0628\u0632\u0631\u06af\u062a\u0631\u06cc\u0646 \u0645\u0648\u062c\u0648\u062f\u0627\u062a \u062c\u0647\u0627\u0646 \u0646\u06cc\u0632 \u0628\u0627\u0634\u062f.",
        "category": "Translation 212.json"
    },
    {
        "instruction": "You are given a sentence in Spanish. Your job is to translate the Spanish sentence into Portugese.",
        "input": "Me gusta hacer cosas nuevas y hacer que ocurran cosas nuevas.",
        "output": "Eu gosto de fazer coisas novas e de as fazer acontecer.",
        "category": "Translation 213.json"
    },
    {
        "instruction": "You are given a sentence in Arabic. Your job is to translate the Arabic sentence into Galician.",
        "input": "\u0648\u064a\u0633\u0645\u0649 \u0645\u0646\u0638\u0627\u0631 \u0645\u0627\u062c\u0644\u0627\u0646 \u0627\u0644\u0639\u0645\u0644\u0627\u0642 (GMT).",
        "output": "Ch\u00e1mase Telescopio Xigante de Magalh\u00e3es, ou GMT (Giant Magellan Telescope).",
        "category": "Translation 214.json"
    },
    {
        "instruction": "You are given a sentence in Arabic. Your job is to translate the Arabic sentence into Italian.",
        "input": "\u0644\u0646\u0628\u062f\u0623 \u0628\u0645\u0631\u0636 \u0627\u0644\u0642\u0644\u0628.",
        "output": "Partiamo dalle malattie cardiache.",
        "category": "Translation 215.json"
    },
    {
        "instruction": "You are given a sentence in Arabic. Your job is to translate the Arabic sentence into Polish.",
        "input": "\u0641\u0647\u064a \u0644\u0627 \u062a\u062a\u0646\u0627\u0633\u0644 \u0648 \u0644\u0627 \u062a\u0648\u062c\u062f \u062d\u062a\u0649 \u0628\u0627\u0644\u062c\u0648\u0627\u0631",
        "output": "Nie rozmna\u017caj\u0105 si\u0119; nie ma ich nawet w pobli\u017cu.",
        "category": "Translation 216.json"
    },
    {
        "instruction": "You are given a sentence in Arabic. Your job is to translate the Arabic sentence into Farsi.",
        "input": "\u0648\u0628\u0627\u0644\u0625\u0639\u062a\u0642\u0627\u062f \u0628\u0623\u0646 \u0647\u0630\u0627 \u0627\u0644\u062a\u0634\u0628\u064a\u0647 \u062d\u0642\u064a\u0642\u064a \u0646\u0643\u062a\u0634\u0641 \u0623\u0646 \u0647\u0646\u0627\u0643 \u0627\u0644\u0643\u062b\u064a\u0631 \u0645\u0646 \u0627\u0644\u062a\u0634\u0627\u0628\u0647 \u0628\u064a\u0646 \u0639\u0645\u0644 \u0627\u0644\u062c\u064a\u0646\u0627\u062a \u0648\u0628\u0631\u0646\u0627\u0645\u062c \u0627\u0644\u0643\u0645\u0628\u064a\u0648\u062a\u0631, \u0647\u0630\u0627 \u0633\u064a\u0633\u0627\u0639\u062f\u0643\u0645 \u0639\u0644\u0649 \u0627\u0644\u0627\u0642\u062a\u0646\u0627\u0639.",
        "output": "\u0628\u0631\u0627\u06cc \u0627\u06cc\u0646\u06a9\u0647 \u062e\u0648\u062f\u062a\u0627\u0646 \u0631\u0627 \u0642\u0627\u0646\u0639 \u06a9\u0646\u06cc\u062f \u06a9\u0647 \u0627\u06cc\u0646 \u062a\u0634\u0628\u06cc\u0647 \u062f\u0631\u0633\u062a \u0627\u0633\u062a \u060c \u0628\u0627\u06cc\u062f \u0628\u062f\u0627\u0646\u06cc\u062f \u06a9\u0647 \u0634\u0628\u0627\u0647\u062a\u0647\u0627\u06cc \u0632\u06cc\u0627\u062f\u06cc \u0628\u06cc\u0646 \u0628\u0631\u0646\u0627\u0645\u0647 \u0647\u0627\u06cc \u0698\u0646\u062a\u06cc\u06a9 \u0648 \u0628\u0631\u0646\u0627\u0645\u0647 \u0647\u0627\u06cc \u06a9\u0627\u0645\u067e\u06cc\u0648\u062a\u0631\u06cc \u0648\u062c\u0648\u062f \u062f\u0627\u0631\u062f \u06a9\u0647 \u0645\u06cc \u062a\u0648\u0627\u0646\u062f \u0634\u0645\u0627 \u0631\u0627 \u0642\u0627\u0646\u0639 \u06a9\u0646\u062f.",
        "category": "Translation 217.json"
    },
    {
        "instruction": "You are given a sentence in Arabic. Your job is to translate the Arabic sentence into Portugese.",
        "input": "\u0627\u062c\u062a\u0645\u0639\u0648\u0627 \u0633\u0648\u064a\u0627 \u0648\u062a\u0639\u0647\u062f\u0648\u0627 665 \u0645\u0644\u064a\u0648\u0646 \u062f\u0648\u0644\u0627\u0631.",
        "output": "Juntaram-se e comprometeram 665 milh\u00f5es de d\u00f3lares.",
        "category": "Translation 218.json"
    },
    {
        "instruction": "Based on the given context, craft a common-sense question, especially those that are LONG, INTERESTING, and COMPLEX. The goal is to write questions that are easy for humans and hard for AI machines! To create such questions, here are some suggestions: A. What may (or may not) be the plausible reason for an event? B. What may (or may not) happen before (or after, or during) an event? C. What may (or may not) be a plausible fact about someone (or something)? D. What may (or may not) happen if an event happens (or did not happen)? You can also create other types of questions. DO NOT make your question answerable without looking at the context, or question of which the correct answer can be directly extracted from the context. DO NOT ask a question that requires very specialized knowledge that is not common sense. DO NOT ask too simple or too short questions. Your question must be related to the context and answerable with common sense. Try to add more variations and complexity to the questions.",
        "input": "Context: He summoned his bottomless bag and started throwing them inside the bag . One of the small boxes he kept outside the bag , and when he grabbed his notebook calender , a small piece of paper sticking out of the top caught his eye . He opened it and noticed that the day 's date was highlighted . The date reminded him of something , but just could n't remember what .",
        "output": "What is probably true ?",
        "category": "Question Generation 22.json"
    },
    {
        "instruction": "You are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into Galician.",
        "input": "\u05d5\u05d4\u05e0\u05d4 \u05e4\u05e8\u05d9\u05d6.",
        "output": "As\u00ed que iso \u00e9 Par\u00eds.",
        "category": "Translation 220.json"
    },
    {
        "instruction": "You are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into Italian.",
        "input": "(\u05e6\u05d7\u05d5\u05e7) \u05d6\u05d0\u05ea \u05d4\u05de\u05e2\u05e8\u05db\u05ea \u05d4\u05d9\u05d5\u05dd... \u05d0\u05d5\u05dc\u05d9 \u05e0\u05db\u05d9\u05df \u05e1\u05e8\u05d8 \u05d5\u05d9\u05d3\u05d0\u05d5?",
        "output": "(Risate) E 'il sistema attuale. Perch\u00e9 non fare un video?",
        "category": "Translation 221.json"
    },
    {
        "instruction": "You are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into Polish.",
        "input": "\u05d5\u05d4\u05dd \u05ea\u05de\u05db\u05d5 \u05d1\u05d9 \u05e7\u05e6\u05ea, \u05d5\u05d1\u05e0\u05d9\u05ea\u05d9 \u05d0\u05ea \u05d6\u05d4.",
        "output": "Dosta\u0142em wsparcie i zbudowa\u0142em je.",
        "category": "Translation 222.json"
    },
    {
        "instruction": "You are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into Farsi.",
        "input": "\u05d9\u05e9 \u05d0\u05e0\u05e9\u05d9\u05dd \u05e9\u05d7\u05d5\u05e9\u05d1\u05d9\u05dd \u05e9\u05d4\u05d3\u05d2\u05de\u05d9\u05dd \u05d4\u05d0\u05dc\u05d4 \u05d1\u05e1\u05d3\u05e8 \u05d2\u05de\u05d5\u05e8, \u05d0\u05d1\u05dc \u05e9\u05d5\u05d0\u05dc\u05d9\u05dd, \"\" \u05d4\u05d0\u05dd \u05d4\u05dd \u05d8\u05d5\u05d1\u05d9\u05dd \u05db\u05de\u05d5 \u05d7\u05d5\u05dc\u05d3\u05d5\u05ea? \u05d4\u05d7\u05d5\u05dc\u05d3\u05d4 \u05d4\u05d9\u05d0 \u05d0\u05d5\u05e8\u05d2\u05e0\u05d9\u05d6\u05dd \u05e9\u05dc\u05dd, \u05d0\u05d7\u05e8\u05d9 \u05d4\u05db\u05dc, \u05e2\u05dd \u05e8\u05e9\u05ea\u05d5\u05ea \u05d0\u05d9\u05d1\u05e8\u05d9\u05dd \u05d4\u05e4\u05d5\u05e2\u05dc\u05d9\u05dd \u05d1\u05d0\u05d9\u05e0\u05d8\u05e8\u05d0\u05e7\u05e6\u05d9\u05d4.",
        "output": "\u0628\u0639\u0636\u06cc \u0645\u0631\u062f\u0645 \u0645\u0645\u06a9\u0646\u0647 \u0641\u06a9\u0631 \u06a9\u0646\u0646 \u0627\u06cc\u0646 \u0645\u062f\u0644\u0647\u0627 \u0628\u0647 \u0646\u0638\u0631 \u062e\u0648\u0628 \u0645\u06cc \u0622\u06cc\u0646\u062f \u0648\u0644\u06cc \u0628\u0627\u0632 \u0645\u06cc \u200c \u067e\u0631\u0633\u0646\u062f: \u0622\u06cc\u0627 \u0627\u06cc\u0646 \u0645\u062f\u0644\u0647\u0627 \u0628\u0647 \u062e\u0648\u0628\u06cc \u0645\u0648\u0634 \u0622\u0632\u0645\u0627\u06cc\u0634\u06af\u0627\u0647\u06cc \u0647\u0633\u062a\u0646 \u061f \u0628\u0647 \u0647\u0631 \u062d\u0627\u0644 \u0645\u0648\u0634\u0647\u0627 \u06cc\u06a9 \u0627\u0631\u06af\u0627\u0646\u0633\u06cc\u0645 \u06a9\u0627\u0645\u0644 \u0647\u0633\u062a\u0646\u062f \u066c \u0645\u062a\u0634\u06a9\u0644 \u0627\u0632 \u062a\u0639\u0627\u0645\u0644 \u0634\u0628\u06a9\u0647 \u0627\u06cc\u06cc \u0639\u0636\u0648\u0647\u0627\u06cc \u0645\u062e\u062a\u0644\u0641",
        "category": "Translation 223.json"
    },
    {
        "instruction": "You are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into Portugese.",
        "input": "\u05d1\u05ea\u05d5\u05d3\u05e2\u05ea\u05e0\u05d5, \u05d3\u05d2\u05d9\u05dd \u05e9\u05d5\u05d7\u05d9\u05dd \u05d0\u05d7\u05d5\u05e8\u05e0\u05d9\u05ea \u05d1\u05db\u05e9\u05db\u05d5\u05e9 \u05e4\u05e8\u05d0\u05d9 \u05e9\u05dc \u05e8\u05d0\u05e9\u05d9\u05d4\u05dd, \u05d5\u05d0\u05e0\u05d7\u05e0\u05d5 \u05d0\u05e4\u05d9\u05dc\u05d5 \u05dc\u05d0 \u05de\u05d1\u05d7\u05d9\u05e0\u05d9\u05dd \u05d1\u05d4\u05dd.",
        "output": "Na nossa mente, os peixes nadam para tr\u00e1s, agitando freneticamente a cabe\u00e7a, e n\u00f3s nem damos por eles.",
        "category": "Translation 224.json"
    },
    {
        "instruction": "Given a sentence in the Japanese, provide an equivalent translation in Bahasa Indonesia that retains the same meaning through the translation. In translation, keep numbers as it is.",
        "input": "\u653f\u5e9c\u306f\u4eba\u3005\u3092\u707d\u5bb3\u304b\u3089\u5b88\u308b\u305f\u3081\u306b\u5341\u5206\u306a\u52aa\u529b\u3092\u3057\u3066\u3044\u306a\u3044\u3002",
        "output": "Selama ini tidak ada upaya yang cukup dari pemerintah untuk melindungi masyarakat dari bencana-bencana.",
        "category": "Translation 225.json"
    },
    {
        "instruction": "Given a sentence in the Indonesian(Bahasa variant), provide an equivalent translation in Japanese that retains the same meaning through the translation. In translation, keep numbers as it is.",
        "input": "Deklarasi telah di setujui dan akan diterbitkan pada hari minggu.",
        "output": "\u5408\u610f\u304c\u4e88\u5b9a\u3055\u308c\u3066\u3044\u308b\u5ba3\u8a00\u306f\u65e5\u66dc\u65e5\u306b\u516c\u8868\u3055\u308c\u308b\u3002",
        "category": "Translation 226.json"
    },
    {
        "instruction": "Given a sentence in the Japanese and Indonesian(Bahasa variant) language. Your task is check if the Bahasa Indonesia sentence is translation of Japanese. if the translation is correct than generate label \"Yes\", otherwise generate label \"No\".",
        "input": "Japanese: \u79d1\u5b66\u8005\u306f\u3001\u6c37\u68da\u304c\u672c\u571f\u304b\u3089\u5206\u65ad\u3055\u308c\u3066\u3044\u308b\u306a\u3089\u3001\u3059\u3067\u306b\u6d6e\u304b\u3093\u3067\u3044\u308b\u306e\u3067\u3001\u6d77\u9762\u4e0a\u6607\u3092\u5f15\u304d\u8d77\u3053\u3059\u3053\u3068\u306f\u306a\u3044\u3001\u3068\u8ff0\u3079\u305f\u3002 \n Bahasa Indonesia: Para ilmuwan berkata bahwa paparan tersebut, jika lepas dari daratannya, tidak akan mengakibatkan peningkatan level air laut, karena ini telah mengambang.",
        "output": "Yes",
        "category": "Text Matching 227.json"
    },
    {
        "instruction": "Given a sentence in the Japanese, provide an equivalent translation in Filipino that retains the same meaning through the translation. In translation, keep numbers as it is.",
        "input": "\u30b2\u30eb\u30c9\u30d5\u30fb\u30e9\u30a4\u30f4\u30fb\u30a8\u30a4\u30c9\u306e\uff12\uff10\u56de\u76ee\u306e\u8a18\u5ff5\u65e5\u306b\u30bb\u30c3\u30c8\u3055\u308c\u308b\u3053\u308c\u3089\u306e\u30b3\u30f3\u30b5\u30fc\u30c8\u306f\u3001\u30a2\u30d5\u30ea\u30ab\u306e\u8ca7\u56f0\u3092\u6e1b\u3089\u305d\u3046\u3068\u3059\u308b\u76ee\u7684\u3067\u3001\u300c\u8ca7\u56f0\u3092\u904e\u53bb\u306e\u3082\u306e\u306b\u300d\u30ad\u30e3\u30f3\u30da\u30fc\u30f3\u3092\u30b5\u30dd\u30fc\u30c8\u3059\u308b\u4e88\u5b9a\u3060\u3063\u305f\u3002",
        "output": "Ang mga konsiyerto na ito ay itinakda sa Ika-20 Anibersaryo ng Geldof's Live Aid, na naipanukala para masuportahan ang kampanya na Make Poverty History, layunin nito na mabawasan ang kahirapan ng mga taga-Africa.",
        "category": "Translation 228.json"
    },
    {
        "instruction": "Given a sentence in the Filipino, provide an equivalent translation in Japanese that retains the same meaning through the translation. In translation, keep numbers as it is.",
        "input": "Binanggit niya ang mga eksepsiyon sa mga kaso ng mga krimen laban sa estado, katulad ng kataksilan at paniniktik.",
        "output": "\u5f7c\u306f\u3001\u4f8b\u3048\u3070\u53cd\u9006\u7f6a\u3068\u30b9\u30d1\u30a4\u6d3b\u52d5\u306e\u3088\u3046\u306a\u3001\u56fd\u5bb6\u306b\u5bfe\u3059\u308b\u72af\u7f6a\u306e\u5834\u5408\u306e\u4f8b\u5916\u3092\u6307\u6458\u3057\u305f\u3002",
        "category": "Translation 229.json"
    },
    {
        "instruction": "Craft one correct answer to the question given in input. To make it more interesting, try to use non-stereotypical language if possible. Make sure your correct answer is reasonably long, consistent with the context, and requires common sense (instead of explicit extraction from the context.) In your answer, use as few words as possible from the given context. Use a response that is uncommon/non-stereotypical, so that it is less predictable. To be less repetitive, please vary your language for each question.",
        "input": "Context: I was staying at hybryd 's place . It was early afternoon and we were idly logged into various lazy entertainments , when someone in a chat room said , \" A plane just flew into the World Trade Center ! \" I did n't know what a World Trade Center was , but I went downstairs and switched on the TV and watched the news coverage . \nQuestion: What will the narrator do after hearing about the news event ?",
        "output": "They will be glued to the TV ., They will call family members .",
        "category": "Question Answering 23.json"
    },
    {
        "instruction": "Given a sentence in the Japanese and Filipino language. Your task is check if the Filipino sentence is translation of Japanese. if the translation is correct than generate label \"Yes\", otherwise generate label \"No\".",
        "input": "Japanese: \u751f\u5b58\u8005\u3092\u63a2\u3059\u6551\u6025\u30c1\u30fc\u30e0\u306f\u3001\u6cd5\u533b\u5b66\u306e\u5c02\u9580\u5bb6\u306b\u3088\u308b\u300c\u7dbf\u5bc6\u306a\u300d\u8a3c\u62e0\u63a2\u3057\u3068\u4e26\u884c\u3057\u3066\u50cd\u3044\u3066\u3044\u308b\u3002 \n Filipino: Ang mga pangkat ng mga sumasagip na manggagawa ay naghahanap ng mga bangkay ay tinatrabaho sa tabi ng mga dalubhasa sa porensiko sa isang \"maselang\" pagsusuri para makita ang ebidensiya.",
        "output": "Yes",
        "category": "Text Matching 231.json"
    },
    {
        "instruction": "Given a sentence in the Japanese, provide an equivalent translation in Filipino that retains the same meaning through the translation. In translation, keep numbers as it is.",
        "input": "\u300c\u5f53\u521d\u306f\u3001\u88c1\u5224\u6240\u306f\u521d\u72af\u8005\u306b\u8efd\u3044\u5211\u3092\u4e0e\u3048\u305f\u3060\u308d\u3046\u300d\u3068\u5f7c\u306f\u8ff0\u3079\u305f\u3002",
        "output": "\u1782\u17b6\u178f\u17cb\u1794\u17b6\u1793\u1793\u17b7\u1799\u17b6\u1799 \"\u1793\u17c5\u1790\u17d2\u1784\u17c3\u178a\u17c6\u1794\u17bc\u1784\u17d7 \u178f\u17bb\u179b\u17b6\u1780\u17b6\u179a\u1793\u17b9\u1784\u1795\u17d2\u178a\u179b\u17cb\u17a2\u17c4\u1799\u1780\u17b7\u1785\u17d2\u1785\u179f\u1793\u17d2\u1799\u17b6\u17a2\u17b6\u1780\u1794\u17d2\u1794\u1780\u17b7\u179a\u17b7\u1799\u17b6\u179b\u17d2\u17a2\u178a\u179b\u17cb\u17a2\u17d2\u1793\u1780\u1794\u17d2\u179a\u1796\u17d2\u179a\u17b9\u178f\u17d2\u178a\u17b7\u1794\u1791\u179b\u17d2\u1798\u17be\u179b\u179b\u17be\u1780\u1791\u17b8\u1798\u17bd\u1799\u1798\u17d2\u1793\u17b6\u1780\u17cb\u17d4\"",
        "category": "Translation 232.json"
    },
    {
        "instruction": "Given a sentence in the Central Khmer, provide an equivalent translation in Japanese that retains the same meaning through the translation. In translation, keep numbers as it is.",
        "input": "\u1798\u17d2\u178f\u1784\u1794\u1793\u17d2\u178f\u17b7\u1785\u17d7 \u1799\u17be\u1784\u1783\u17be\u1789\u1780\u17b8\u17a1\u17b6\u1793\u17b6\u179a\u17b8\u1787\u17b6\u1789\u17b9\u1780\u1789\u17c9\u17b6\u1794\u17cb\u178f\u17d2\u179a\u17bc\u179c\u1794\u17b6\u1793\u1782\u17c1\u1799\u1780\u1798\u1780\u178a\u17b6\u1780\u17cb\u1780\u17d2\u1793\u17bb\u1784\u1780\u17b6\u179a\u1795\u17d2\u179f\u1796\u17d2\u179c\u1795\u17d2\u179f\u17b6\u1799\u179f\u17c6\u1781\u17b6\u1793\u17cb\u17d7\u17d4",
        "output": "\u5f90\u3005\u306b\u3001\u79c1\u305f\u3061\u306f\u4e3b\u6d41\u306e\u30e1\u30c7\u30a3\u30a2\u51fa\u7248\u7269\u3067\u3088\u308a\u983b\u7e41\u306b\u5973\u5b50\u30b9\u30dd\u30fc\u30c4\u306e\u7279\u96c6\u3092\u898b\u308b\u3088\u3046\u306b\u306a\u3063\u3066\u3044\u307e\u3059\u3002",
        "category": "Translation 233.json"
    },
    {
        "instruction": "Given a sentence in the Japanese and Central Khmer language. Your task is check if the Khamer sentence is translation of Japanese. if the translation is correct than generate label \"Yes\", otherwise generate label \"No\".",
        "input": "Japanese: CNN\u306b\u3088\u308b\u3068\u3001\u30d7\u30e9\u30b9\u30c1\u30c3\u30af\u88fd\u306e\u8cb7\u3044\u7269\u888b\u3092\u7981\u6b62\u3057\u305f\u308a\u5236\u9650\u3057\u305f\u306e\u306f\u4e2d\u83ef\u4eba\u6c11\u5171\u548c\u56fd\u304c\u6700\u521d\u306e\u56fd\u3067\u306f\u306a\u304f\u3001\u30a6\u30ac\u30f3\u30c0\u3068\u5357\u30a2\u30d5\u30ea\u30ab\u304c\u8a18\u9332\u3055\u308c\u3066\u3044\u308b\u3002 \n Khamer: \u179f\u17b6\u1792\u17b6\u179a\u178e\u179a\u178a\u17d2\u178b\u1794\u17d2\u179a\u1787\u17b6\u1798\u17b6\u1793\u17b7\u178f\u1785\u17b7\u1793\u1798\u17b7\u1793\u1798\u17c2\u1793\u1787\u17b6\u1794\u17d2\u179a\u1791\u17c1\u179f\u1791\u17b8\u1798\u17bd\u1799\u178a\u17c2\u179b\u17a0\u17b6\u1798\u1783\u17b6\u178f\u17cb\u17ac\u179a\u17b9\u178f\u1794\u1793\u17d2\u178f\u17b9\u1784\u1791\u17c5\u179b\u17be\u1780\u17b6\u179a\u1794\u17d2\u179a\u17be\u1794\u17d2\u179a\u17b6\u179f\u17cb\u1790\u1784\u17cb\u1795\u17d2\u179b\u17b6\u179f\u17d2\u1791\u17b7\u1785\u17a1\u17be\u1799 \u1780\u17cf\u1798\u17b6\u1793\u1780\u17b6\u179a\u1780\u178f\u17cb\u179f\u17c6\u1782\u17b6\u179b\u17cb\u178a\u17bc\u1785\u1793\u17c1\u17c7\u1793\u17c5\u1794\u17d2\u179a\u1791\u17c1\u179f\u178a\u17bc\u1785\u1787\u17b6 \u200b\u1799\u17bc\u17a0\u17d2\u1782\u17c1\u1793\u178a\u17b6 \u1793\u17b7\u1784\u17a2\u17b6\u17a0\u17d2\u179a\u17d2\u179c\u17b7\u1785\u1781\u17b6\u1784\u178f\u17d2\u1794\u17bc\u1784 \u1793\u17c1\u17c7\u1794\u17be\u1799\u17c4\u1784\u178f\u17b6\u1798\u179a\u1799\u17c8\u1796\u178f\u17cc\u1798\u17b6\u1793\u179f\u17ca\u17b8\u17a2\u17c1\u1793\u17a2\u17c1\u1793\u17d4",
        "output": "Yes",
        "category": "Text Matching 234.json"
    },
    {
        "instruction": "Given a sentence in the Japanese, provide an equivalent translation in Lao that retains the same meaning through the translation. In translation, keep numbers as it is.",
        "input": "\u30cf\u30a4\u30ab\u30fc\u96c6\u56e3\u304cTanzhangxia\u5ce1\u8c37\u306e\u9032\u5165\u7981\u6b62\u533a\u57df\u306b\u30ac\u30a4\u30c9\u3068\u3068\u3082\u306b\u5165\u3063\u305f\u3068\u4f1d\u3048\u3089\u308c\u3066\u3044\u308b\u3002",
        "output": "\u0ea1\u0eb5\u0e81\u0eb2\u0e99\u0ea5\u0eb2\u0e8d\u0e87\u0eb2\u0e99\u0ea7\u0ec8\u0eb2 \u0e81\u0eb8\u0ec8\u0ea1\u0e99\u0eb1\u0e81\u0e9b\u0eb5\u0e99\u0e9e\u0eb9\u0ec4\u0e94\u0ec9\u0ec0\u0e82\u0ebb\u0ec9\u0eb2\u0ec4\u0e9b\u0ec3\u0e99\u0ec0\u0e82\u0e94\u0eab\u0ea7\u0e87\u0eab\u0ec9\u0eb2\u0ea1 \u0e82\u0ead\u0e87\u0eae\u0ec8\u0ead\u0ea1\u0e9e\u0eb9 \u0e97\u0eb1\u0e99\u0e8a\u0ecc\u0eae\u0eb1\u0e87\u0ec0\u0e8a\u0e8d \u0e81\u0eb1\u0e9a\u0e9c\u0eb9\u0ec9\u0e99\u0eb3\u0e97\u0ec8\u0ebd\u0ea7.",
        "category": "Translation 235.json"
    },
    {
        "instruction": "Given a sentence in the Lao, provide an equivalent translation in Japanese that retains the same meaning through the translation. In translation, keep numbers as it is.",
        "input": "\u0ea5\u0eb2\u0ea7\u0ec4\u0e94\u0ec9\u0e81\u0ea7\u0ec8\u0eb2\u0ea7\u0ec8\u0eb2 \"\u0e81\u0eb2\u0e99\u0ec2\u0e84\u0eaa\u0eb0\u0e99\u0eb2\u0e82\u0ecd\u0ec9\u0ea1\u0eb9\u0e99\u0ec1\u0e81\u0ec8\u0e9b\u0eb0\u0e8a\u0eb2\u0e8a\u0ebb\u0e99 \u0e81\u0ec8\u0ebd\u0ea7\u0e81\u0eb1\u0e9a \u0e81\u0eb2\u0e99\u0ec1\u0e82\u0ea7\u0e99\u0e84\u0ecd\u0e95\u0eb2\u0e8d\" \u0eaa\u0eb2\u0ea1\u0eb2\u0e94\u0ec0\u0e9b\u0eb1\u0e99\u0e97\u0eb2\u0e87\u0edc\u0eb7\u0ec8\u0e87\u0ec3\u0e99\u0e81\u0eb2\u0e99\u0eab\u0ebc\u0eb8\u0e94\u0e9c\u0ec8\u0ead\u0e99\u0ead\u0eb1\u0e94\u0e95\u0eb2.",
        "output": "\u5f7c\u306f\u300c\u9996\u540a\u308a\u306b\u3064\u3044\u3066\u306e\u516c\u5171\u60c5\u5831\u30ad\u30e3\u30f3\u30da\u30fc\u30f3\u300d\u306f\u7387\u3092\u4f4e\u304f\u3059\u308b\u305f\u3081\u306e\u4e00\u3064\u306e\u65b9\u6cd5\u306b\u306a\u308a\u3046\u308b\u3068\u8a00\u3063\u305f\u3002",
        "category": "Translation 236.json"
    },
    {
        "instruction": "Given a sentence in the Japanese and Lao language. Your task is check if the Lao sentence is translation of Japanese. if the translation is correct than generate label \"Yes\", otherwise generate label \"No\".",
        "input": "Japanese: \u8a34\u8a1f\u306e\u539f\u544a\u306b\u306f\u3001\u30ad\u30ea\u30b9\u30c8\u6559\u3084\u30d2\u30f3\u30ba\u30fc\u6559\u304b\u3089\u6539\u5b97\u3057\u305f\u4eba\u3082\u3044\u305f\u3002 \n Lao: \u0e95\u0ebb\u0ec9\u0e99\u0e9b\u0eb5 2006 \u0eaa\u0eb0\u0e9e\u0eb2\u0ec4\u0e94\u0ec9\u0e96\u0eb7\u0e81\u0e81\u0ec8\u0eb2\u0ea7\u0eab\u0eb2\u0e88\u0eb2\u0e81\u0e84\u0ebb\u0e99\u0ea7\u0ebb\u0e87\u0ec3\u0e99\u0eaa\u0eb0\u0e9e\u0eb2 \u0e9c\u0ec8\u0eb2\u0e99\u0e9a\u0eae\u0eca\u0ead\u0e81 \u0ec3\u0e99\u0e9b\u0eb0\u0ec0\u0e94\u0eb1\u0e99\u0eae\u0eb9\u0e9a\u0ec1\u0e9a\u0e9a\u0e82\u0ead\u0e87\u0e9a\u0ebb\u0e94\u0ea5\u0eb2\u0e8d\u0e87\u0eb2\u0e99.",
        "output": "No",
        "category": "Text Matching 237.json"
    },
    {
        "instruction": "Given a sentence in the Japanese, provide an equivalent translation in Thai that retains the same meaning through the translation. In translation, keep numbers as it is.",
        "input": "AWG-LCA\u306f\u30016\u6708\u306e\u4ea4\u6e09\u30bb\u30c3\u30b7\u30e7\u30f3\u306e\u524d\u306b\u65b0\u3057\u3044\u300cCOP16\u306e\u4ea4\u6e09\u30c6\u30ad\u30b9\u30c8\u300d\u3092\u4f5c\u308b\u3053\u3068\u3092\u8ab2\u3055\u308c\u3066\u3044\u308b\u4ea4\u6e09\u30b0\u30eb\u30fc\u30d7\u3067\u3042\u308b\u3002",
        "output": "\u0e01\u0e25\u0e38\u0e48\u0e21 AWG-LCA \u0e21\u0e35\u0e20\u0e32\u0e23\u0e01\u0e34\u0e08\u0e2a\u0e48\u0e07 \"\u0e02\u0e49\u0e2d\u0e04\u0e27\u0e32\u0e21\u0e40\u0e08\u0e23\u0e08\u0e32 COP16\" \u0e2b\u0e25\u0e31\u0e07\u0e08\u0e32\u0e01\u0e01\u0e32\u0e23\u0e1b\u0e23\u0e30\u0e0a\u0e38\u0e21\u0e40\u0e08\u0e23\u0e08\u0e32\u0e43\u0e19\u0e40\u0e14\u0e37\u0e2d\u0e19\u0e21\u0e34\u0e16\u0e38\u0e19\u0e32\u0e22\u0e19",
        "category": "Translation 238.json"
    },
    {
        "instruction": "Given a sentence in the Thai, provide an equivalent translation in Japanese that retains the same meaning through the translation. In translation, keep numbers as it is.",
        "input": "Deal \u0e2d\u0e18\u0e34\u0e1a\u0e32\u0e22\u0e40\u0e2b\u0e15\u0e38\u0e1c\u0e25\u0e02\u0e2d\u0e07\u0e40\u0e02\u0e32\u0e43\u0e19\u0e01\u0e32\u0e23\u0e2a\u0e07\u0e2a\u0e31\u0e22\u0e04\u0e27\u0e32\u0e21\u0e02\u0e31\u0e14\u0e41\u0e22\u0e49\u0e07\u0e17\u0e32\u0e07\u0e1c\u0e25\u0e1b\u0e23\u0e30\u0e42\u0e22\u0e0a\u0e19\u0e4c\u0e01\u0e31\u0e1a\u0e19\u0e31\u0e01\u0e02\u0e48\u0e32\u0e27\u0e02\u0e2d\u0e07 Wikinews",
        "output": "JustenDeal\u306f\u3001\u30a6\u30a3\u30ad\u30cb\u30e5\u30fc\u30b9\u306e\u30ea\u30dd\u30fc\u30bf\u30fc\u306b\u5229\u5bb3\u5bfe\u7acb\u3092\u7591\u3046\u7406\u7531\u3092\u8a18\u8ff0\u3057\u305f\u3002",
        "category": "Translation 239.json"
    },
    {
        "instruction": "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.",
        "input": "Context: She drags me down the street until she gets to a spot she wants to smell then she abruptly stops and I stumble forward . This goes on until she has done number one and number two then we have a nice leisurely walk back to Denis ' with plenty of time for her to stop and smell the other dog 's pee . From what Denis mention Miyoko is more drill sergeant with Ivy there are lots of comands and heels and Ivy is a free spirit she does n't want to heel . Tonight I had Little Tony 's with Ipants ( Ira ) it was a post birthday dinner . \nQuestion: Why is Ivy being yelled at so vigorously by Denis ? \nCorrect Answer: Ivy is difficult to train .",
        "output": "Ivy has hit someone ., Ivy is biting people .",
        "category": "Wrong Candidate Generation 24.json"
    },
    {
        "instruction": "Given a sentence in the Japanese and Thai language. Your task is check if the Filipino sentence is translation of Japanese. if the translation is correct than generate label \"Yes\", otherwise generate label \"No\".",
        "input": "Japanese: \u30d9\u30f3\u6c0f\u306f\u5f7c\u304c\u3064\u306d\u306bBBC\u306e\u652f\u6301\u8005\u3060\u3063\u305f\u3068\u8a00\u3044\u3001\u6628\u65e5\u306f\u305d\u308c\u3092\u6551\u6025\u30b5\u30fc\u30d3\u30b9\u3068\u6bd4\u8f03\u3057\u305f\u3002 \n Thai: \u0e15\u0e32\u0e21\u0e17\u0e35\u0e48 Le Nouvel Observateur \u0e23\u0e32\u0e22\u0e07\u0e32\u0e19\u0e1e\u0e1a\u0e27\u0e48\u0e32\u0e2b\u0e19\u0e36\u0e48\u0e07\u0e40\u0e14\u0e37\u0e2d\u0e19\u0e2b\u0e25\u0e31\u0e07\u0e08\u0e32\u0e01\u0e17\u0e35\u0e48\u0e21\u0e35\u0e01\u0e32\u0e23\u0e2a\u0e37\u0e1a\u0e2a\u0e27\u0e19\u0e14\u0e49\u0e32\u0e19\u0e41\u0e23\u0e07\u0e07\u0e32\u0e19\u0e40\u0e01\u0e34\u0e14\u0e02\u0e36\u0e49\u0e19 \u0e17\u0e32\u0e07\u0e2a\u0e32\u0e02\u0e32\u0e43\u0e19\u0e1d\u0e23\u0e31\u0e48\u0e07\u0e40\u0e28\u0e2a\u0e02\u0e2d\u0e07\u0e1a\u0e23\u0e34\u0e29\u0e31\u0e17\u0e01\u0e47\u0e44\u0e14\u0e49\u0e2a\u0e25\u0e32\u0e22\u0e15\u0e31\u0e27\u0e25\u0e07",
        "output": "No",
        "category": "Text Matching 240.json"
    },
    {
        "instruction": "You will be given two pieces of text with the same meaning. One of them is simpler and easier to understand for non-native English speakers. Complex texts may contain more difficult words, have unnecessary phrases or contain long sentences. Your task is to choose the simpler piece of text. You are expected to output 'Text one' if the first sentence is simpler. Otherwise output 'Text two'.",
        "input": "Text one: Tiko United FC is a Cameroonian football club based in Tiko.\n Text two: Tiko United is a football club in Tiko.",
        "output": "Text two",
        "category": "Text Simplification 241.json"
    },
    {
        "instruction": "In this task, you need to count the number of times the given letter appears in the given sentence.",
        "input": "Sentence: 'the skiers are enjoying the mountain of fresh powder'. Find frequency of the letter 'f'",
        "output": "2",
        "category": "Program Execution 252.json"
    },
    {
        "instruction": "In this task, you need to answer 'Yes' if the given word is the longest word (in terms of number of letters) in the given sentence, else answer 'No'. Note that there could be multiple longest words in a sentence as they can have the same length that is the largest across all words in that sentence.",
        "input": "Sentence: 'fire hydrant covered in snow in front of house and trees'. Is 'hydrant' the longest word in the sentence?",
        "output": "Yes",
        "category": "Linguistic Probing 263.json"
    },
    {
        "instruction": "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.",
        "input": "This is not about your education level or how good your grades are .",
        "output": "no",
        "category": "Text Categorization 274.json"
    },
    {
        "instruction": "In this task, you're given a paragraph from the research paper and your task is to generate a suitable title for the research paper based on the given paper. Under 100 words is a good title length.",
        "input": "Cytokine storm during viral infection is a prospective predictor of morbidity and mortality, yet the cellular sources remain undefined. Here, using genetic and chemical tools to probe functions of the S1P 1 receptor, we elucidate cellular and signaling mechanisms that are important in initiating cytokine storm. Whereas S1P 1 receptor is expressed on endothelial cells and lymphocytes within lung tissue, S1P 1 agonism suppresses cytokines and innate immune cell recruitment in wild-type and lymphocyte-deficient mice, identifying endothelial cells as central regulators of cytokine storm. Furthermore, our data reveal immune cell infiltration and cytokine production as distinct events that are both orchestrated by endothelial cells. Moreover, we demonstrate that suppression of early innate immune responses through S1P 1 signaling results in reduced mortality during infection with a human pathogenic strain of influenza virus. Modulation of endothelium with a specific agonist suggests that diseases in which amplification of cytokine storm is a significant pathological component could be chemically tractable.",
        "output": "Endothelial Cells Are Central Orchestrators of Cytokine Amplification during Influenza Virus Infection",
        "category": "Title Generation 275.json"
    },
    {
        "instruction": "In this task, you're given a paragraph and title from the research paper. Your task is to classify whether the given title is suitable or not for the research paper based on the given paragraph. Return \"True\" if title is proper according to paragraph else \"False\".",
        "input": "Paragraph: Viral bronchiolitis is a common clinical syndrome aff ecting infants and young children. Concern about its associated morbidity and cost has led to a large body of research that has been summarised in systematic reviews and integrated into clinical practice guidelines in several countries. The evidence and guideline recommendations consistently support a clinical diagnosis with the limited role for diagnostic testing for children presenting with the typical clinical syndrome of viral upper respiratory infection progressing to the lower respiratory tract. Management is largely supportive, focusing on maintaining oxygenation and hydration of the patient. Evidence suggests no benefi t from bronchodilator or corticosteroid use in infants with a fi rst episode of bronchiolitis. Evidence for other treatments such as hypertonic saline is evolving but not clearly defi ned yet. For infants with severe disease, the insuffi cient available data suggest a role for high-fl ow nasal cannula and continuous positive airway pressure use in a monitored setting to prevent respiratory failure. \n Title: Viral bronchiolitis",
        "output": "True",
        "category": "Text Matching 276.json"
    },
    {
        "instruction": "In this task, you are given a sentence from the research paper and your task is to classify the given sentence into the following categories: Background (Why is this problem important? What relevant works have been created before? What is still missing in the previous works? What are the high-level research questions? How might this help other research or researchers?), Purpose (What specific things do the researchers want to do? What specific knowledge do the researchers want to gain? What specific hypothesis do the researchers want to test?), Method (How did the researchers do the work or find what they sought? What are the procedures and steps of the research?), or Finding (What did the researchers find out? Did the proposed methods work? Did the thing behave as the researchers expected?). ",
        "input": "We compare our results across several variants of Susceptible-Infectious-Recovered ( SIR ) compartmental models to quantify the impact of modeling assumptions on our estimates.",
        "output": "method",
        "category": "Section Classification 277.json"
    },
    {
        "instruction": "In this task, you are given a sentence from the research paper and the category to which it belongs. Your task is to classify whether the given category is correct or not by providing \"True\" and \"False\", respectively. Here are the definitions for the categories: Background (Why is this problem important? What relevant works have been created before? What is still missing in the previous works? What are the high-level research questions? How might this help other research or researchers?), Purpose (What specific things do the researchers want to do? What specific knowledge do the researchers want to gain? What specific hypothesis do the researchers want to test?), Method (How did the researchers do the work or find what they sought? What are the procedures and steps of the research?), or Finding (What did the researchers find out? Did the proposed methods work? Did the thing behave as the researchers expected?). \",",
        "input": "Sentence: We suggest this fraction may be useful in treating ALI. \n Section: finding",
        "output": "True",
        "category": "Section Classification 278.json"
    },
    {
        "instruction": "In this task, based on the given context word, you are asked to create a pair of sentences each containing a blank (_). The sentence pair should look similar and should be about two different persons (PersonX and PersonY). Additionally, the two sentences must be different in terms of trigger words (e.g., \"sympathetic\" and \"stern\") which express contrasting attributes about the two persons. The answer to the first and the second sentence must be PersonX and PersonY, respectively. PersonX and PersonY should not be equally likely to fill the blank. For each sentence, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people (e.g., Donald Trump, Putin, etc.) in your sentences. Avoid repeating the same style or phrase in twin sentences e.g., a contrasting sentence can always be created using simple negation i.e. by adding not, never, etc. Instead, try to increase diversity. Both twin sentences must contain at least 15 and at most 30 words. Twin sentences must have at least 70% overlapping words. You must utilize the given context word while writing the twin sentences. Each of the twin sentences must contain only one blank. Make sure that PersonX and PersonY have the same gender. In each sentence, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY.",
        "input": "Context Word: collector.",
        "output": "Sentence 1: The collector bought more items from PersonX than PersonY because _ had a large collection to choose from. \nSentence 2: The collector bought more items from PersonX than PersonY because _ had a small collection to choose from.",
        "category": "Question Generation 29.json"
    },
    {
        "instruction": "In this task, you are given a statement spoken by a politician in natural language and the subject of the discussion for the given statement. Your task is to determine if the given subject of the discussion is correct for the given statement. The subject can be multiple words. Answer with \"True\" if it's the correct subject of discussion or return \"False\" if it's incorrect.",
        "input": "Statement: The number of people in Atlanta dying from HIV and AIDS declined 59 percent between 2004 and 2012. \n Subject: public-health",
        "output": "True",
        "category": "Text Categorization 302.json"
    },
    {
        "instruction": "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.",
        "input": "Context Word: debris.",
        "output": "PersonX tripped over the debris in the road unlike PersonY, because _ is very careless and clumsy.",
        "category": "Question Generation 31.json"
    },
    {
        "instruction": "Given a disfluent sentence, modify the sentence to it to its equivalent fluent form, preserving the meaning of the sentence.",
        "input": "Is the connection sorry the packet header long?",
        "output": "Is the packet header long ",
        "category": "Question Rewriting 311.json"
    },
    {
        "instruction": "In this task, you are given a tuple, comprising Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether, as a result of the Head, PersonY or others will be affected as mentioned in the Tail or not. These effects are social actions that may occur after the Head event. For example, X may get hugged, and Y may blush in response. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.",
        "input": "Head: PersonX moves PersonY's ___ away<sep>Tail: jumps",
        "output": "Yes",
        "category": "Commonsense Classification 312.json"
    },
    {
        "instruction": "In this task, you are given a tuple, comprising Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether, as a result of the Head, PersonY, or others, feel what is mentioned in the Tail or not. Feelings in this task are the emotional reactions on the part of PersonY or other participants in an event. For example, as a result of gift-giving, others (in this case, PersonY) might feel appreciated. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.",
        "input": "Head: PersonX affects PersonY's interests<sep>Tail: lose money",
        "output": "No",
        "category": "Commonsense Classification 313.json"
    },
    {
        "instruction": "In this task, you are given a tuple, comprising Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether, as a result of the Head, PersonY or others will want what is mentioned in the Tail or not. In this task, wanting is a postcondition desire on the part of PersonY and others, respectively. For example, as a result of PersonX giving PersonY gifts, PersonY may want to open the gift. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.",
        "input": "Head: PersonX makes another effort<sep>Tail: them to stop",
        "output": "Yes",
        "category": "Commonsense Classification 314.json"
    },
    {
        "instruction": "In this task, you are given a tuple, comprising Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether, as a result of the Head, PersonX will be seen as what is mentioned in the Tail or not. In this task, PersonX will be seen as the Tail if the Tail describes PersonX's persona or attribute as perceived by others given an event. In the gift-giving example, X may be seen as generous or giving. In contrast, in an event such as PersonX steals a car, PersonX may be perceived as evil. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.",
        "input": "Head: PersonX always wore<sep>Tail: to ask PersonX where they got their clothes",
        "output": "No",
        "category": "Commonsense Classification 315.json"
    },
    {
        "instruction": "In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether, as a result of the Head, PersonX will be affected as mentioned in the Tail or not. These effects are social actions that may occur after the Head event. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.",
        "input": "Head: PersonX grabs PersonX's tools<sep>Tail: fixes something",
        "output": "Yes",
        "category": "Commonsense Classification 317.json"
    },
    {
        "instruction": "In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether The Tail is the intention of the PersonX from the Head or not. The intention is the likely intent or desire of PersonX behind the execution of an event. For example, given the Head PersonX gives PersonY gifts, an intention might be that PersonX wanted to be thoughtful. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.",
        "input": "Head: PersonX addresses PersonY audience<sep>Tail: introduces PersonY",
        "output": "No",
        "category": "Commonsense Classification 318.json"
    },
    {
        "instruction": "In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether PersonX needs what is mentioned in the Tail before the Head or not. Here need is a precondition for PersonX to achieve the event. For example, in order for PersonX to give PersonY gifts, PersonX must first buy the presents. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.",
        "input": "Head: PersonX asks PersonY's grandma<sep>Tail: happy",
        "output": "No",
        "category": "Commonsense Classification 319.json"
    },
    {
        "instruction": "You need to answer a given question containing a blank (_). Your answer must be one of the two objects mentioned in the question, for example \"trophy\" and \"suitcase\". Your answer must not contain a word that is not present in the question. Please don't use articles (e.g., the, a) before the answer.",
        "input": "Rather than wearing shorts, Angela wore a skirt because the _ would make the boys take notice, something she desired.",
        "output": "skirt",
        "category": "Coreference Resolution 32.json"
    },
    {
        "instruction": " In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether, as a result of the Head, PersonX may feel what is mentioned in the Tail or not. In this task, the feeling is an emotional reaction on the part of X or other participants in an event. For example, as a result of gift-giving, X might feel good about [one]self. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.",
        "input": "Head: PersonX faces another ___<sep>Tail: successful.",
        "output": "Yes",
        "category": "Commonsense Classification 320.json"
    },
    {
        "instruction": "In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether the Head can be hindered by what is mentioned in the Tail or not. In this task, hindering introduces hindrances that obstruct the natural path to the achievement of a goal. For example, the event PersonX adopts a cat can be obstructed if PersonX is allergic to cats. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person,  and/or an action.",
        "input": "Head: PersonX accepts PersonY's invitation<sep>Tail: forgets about it",
        "output": "No",
        "category": "Commonsense Classification 321.json"
    },
    {
        "instruction": "In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether the Head happens after the Tail or not. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.",
        "input": "Head: PersonX abolishes ___ altogether<sep>Tail: strict",
        "output": "No",
        "category": "Commonsense Classification 322.json"
    },
    {
        "instruction": "In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether the Head happens before the Tail or not. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.",
        "input": "Head: PersonX accepts PersonY appointment<sep>Tail: says congrats",
        "output": "No",
        "category": "Commonsense Classification 323.json"
    },
    {
        "instruction": "In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether the Head is located or can be found at/in/on the Tail or not. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.",
        "input": "Head: PersonX accuses PersonY of cheating<sep>Tail: envious",
        "output": "No",
        "category": "Commonsense Classification 324.json"
    },
    {
        "instruction": "In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether the Head is used for the Tail or not. The usage describes everyday affordances or uses of objects and includes both typical and atypical uses. For example, a popcorn bucket can typically be used to hold popcorn, but it could also serve as a hat in atypical situations. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.",
        "input": "Head: sun<sep>Tail: shine",
        "output": "Yes",
        "category": "Commonsense Classification 326.json"
    },
    {
        "instruction": "In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether the Head is a part, portion, or makeup of the Tail or not. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.",
        "input": "Head: door<sep>Tail: latch",
        "output": "Yes",
        "category": "Commonsense Classification 328.json"
    },
    {
        "instruction": "In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether the Head includes an event or an action in the Tail or not. This happens when the Tail denotes a step within the larger head event. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.",
        "input": "Head: PersonX believes every word<sep>Tail: Gullible",
        "output": "No",
        "category": "Commonsense Classification 329.json"
    },
    {
        "instruction": "In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether the Head can be characterized by being or having the Tail or not. Being characterized usually describes entities' general characteristics such as rose is red, or subjective attributes such as thirst is uncomfortable. It can also map to descriptors that speak to the substance or value of items such as meat has the property of being stored in the freezer or bike is powered by a person's legs. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.",
        "input": "Head: PersonX achieves PersonY objective<sep>Tail: encourage them",
        "output": "No",
        "category": "Commonsense Classification 330.json"
    },
    {
        "instruction": "In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether it is plausible for the Head to desire the Tail or not. In this task, desire means desires of sentient entities. For example, doctors likely desire to cure a patient. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.",
        "input": "Head: PersonX answers the door<sep>Tail: goes inside",
        "output": "No",
        "category": "Commonsense Classification 331.json"
    },
    {
        "instruction": "In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether, as a result of the Head, PersonX wants what is mentioned in the Tail or not. In this task, wanting is a postcondition desire on the part of PersonX, respectively. As a result of PersonX giving PersonY gifts, PersonX may also desire to hug PersonY. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.",
        "input": "Head: PersonX buys ___ in advance<sep>Tail: To take advantage of an offer",
        "output": "Yes",
        "category": "Commonsense Classification 332.json"
    },
    {
        "instruction": "In this task, you are given two phrases: Head and Tail, separated with <sep>. The Head and the Tail events are short phrases possibly involving participants. The names of specific people have been replaced by generic words (e.g., PersonX, PersonY, PersonZ). PersonX is always the subject of the event. You have to determine whether the Head is capable of the Tail or not. Being capable of something includes general capabilities, such as a human is capable of thinking and reasoning or drinking coffee. It also includes specialized capabilities such as a surgeon is capable of operating on a patient. Classify your answers into \"Yes\" and \"No\". The phrase may also contain \"___\", a placeholder that can be an object, a person, and/or an action.",
        "input": "Head: PersonX accomplishes PersonX's purposes<sep>Tail: honor it to parents",
        "output": "No",
        "category": "Commonsense Classification 333.json"
    },
    {
        "instruction": "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.",
        "input": "PersonX tucks ___ behind PersonY's ear",
        "output": "pencil, hair, string, coins, flower, food, gum",
        "category": "Fill in The Blank 335.json"
    },
    {
        "instruction": "You are given a sentence in English. Your job is to translate the English sentence into Japanese.",
        "input": "I'm going to show you a very quick clip to show you how I painted and a little bit about my city, Bangalore.",
        "output": "\u79c1\u304c\u3069\u3093\u306a\u98a8\u306b\u63cf\u3044\u305f\u304b\u3061\u3087\u3063\u3068\u3057\u305f\u30af\u30ea\u30c3\u30d7\u304c\u3042\u308a\u307e\u3059\u6545\u90f7\u306e\u30d0\u30f3\u30ac\u30ed\u30fc\u30eb\u3067\u3059",
        "category": "Translation 336.json"
    },
    {
        "instruction": "You are given a sentence in English. Your job is to translate the English sentence into Spanish.",
        "input": "So this coal will last a little bit more than a month.",
        "output": "Por lo tanto, este carb\u00f3n durar\u00eda poco m\u00e1s de un mes.",
        "category": "Translation 337.json"
    },
    {
        "instruction": "You are given a sentence in English. Your job is to translate the English sentence into Arabic.",
        "input": "What kind of a world can we be making? \"\" are treated with more and more skepticism, and move off the table.",
        "output": "\u0623\u064a \u0646\u0648\u0639 \u0645\u0646 \u0627\u0644\u0639\u0627\u0644\u0645 \u0646\u0633\u062a\u0637\u064a\u0639 \u0623\u0646 \u0646\u0639\u0645\u0644 \u061f \u064a\u062a\u0645 \u0627\u0644\u062a\u0639\u0627\u0645\u0644 \u0645\u0639 \u0627\u0644\u0645\u0632\u064a\u062f \u0648\u0627\u0644\u0645\u0632\u064a\u062f \u0645\u0646 \u0627\u0644\u0634\u0643\u0648\u0643 \u0648\u0627\u0644\u0627\u0646\u062a\u0642\u0627\u0644 \u0645\u0646 \u0639\u0644\u0649 \u0627\u0644\u0637\u0627\u0648\u0644\u0629.",
        "category": "Translation 339.json"
    },
    {
        "instruction": "You're given a fill-in-the-blank question where the answer is PersonX. You need to minimally change the given question so that the answer flips to PersonY. This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"sympathetic\" to \"stern\"). You should not change any content in the given question beyond a word or two i.e. the trigger word/phrase. PersonX and PersonY should not be equally likely to fill the blank. For your question, PersonY should be a well-agreed answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use the names of real people or generic names (e.g., Donald Trump, John Doe, etc.) in your question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. Make sure that PersonX and PersonY have the same gender. In your question, PersonX and PersonY should be used only ONCE and PersonX should appear earlier than PersonY. Although there are many correct answers, you only need to write one of them.",
        "input": "Context Word: homemade. \nQuestion: PersonX kept a well stocked kitchen while PersonY did not, so _ always had homemade food. \nAnswer: PersonX",
        "output": "PersonX kept a well stocked kitchen while PersonY did not, so _ never had homemade food.",
        "category": "Question Rewriting 34.json"
    },
    {
        "instruction": "You are given a sentence in English. Your job is to translate the English sentence into Hebrew.",
        "input": "Every single grain is different. There are no two grains of sand alike in the world.",
        "output": "\u05db\u05dc \u05d2\u05e8\u05d2\u05e8 \u05d7\u05d5\u05dc \u05d4\u05d5\u05d0 \u05e9\u05d5\u05e0\u05d4. \u05d0\u05d9\u05df \u05e9\u05e0\u05d9 \u05d2\u05e8\u05d2\u05e8\u05d9\u05dd \u05e9\u05dc \u05d7\u05d5\u05dc \u05d6\u05d4\u05d9\u05dd \u05d1\u05e2\u05d5\u05dc\u05dd.",
        "category": "Translation 340.json"
    },
    {
        "instruction": "You are given a sentence in Japanese. Your job is to translate the Japanese sentence into English.",
        "input": "\u266b \u60f3\u50cf\u3057\u3066\u3054\u3089\u3093\u4e00\u4eba\u307c\u3063\u3061\u306e\u4e16\u754c \u266b \u266b \u8ab0\u3082\u3044\u306a\u3044\u3093\u3060 \u266b \u266b \u3064\u3044\u3055\u3063\u304d\u307e\u3067\u306e\u58f0\u3084\u9854\u306f \u266b \u266b \u3069\u3053\u304b\u3078\u6d88\u3048\u3066\u3057\u307e\u3063\u305f \u266b \u266b \u8a00\u3046\u3079\u304d\u3053\u3068\u306f\u8a00\u3063\u305f\u3055 \u266b \u266b \u3082\u3046\u8a71\u3059\u76f8\u624b\u3082\u3044\u306a\u3044\u3051\u3069 \u266b \u266b Oh \u3088\u304f\u805e\u3044\u3066\u304f\u308c \u266b \u266b \u3069\u3093\u306a\u3084\u3064\u3067\u3082\u4f55\u8005\u304b\u306b\u306a\u308c\u308b\u3093\u3060 \u266b \u266b \u4f55\u304b\u3092\u5909\u3048\u3089\u308c\u308b\u3093\u3060 \u266b \u266b \u3069\u3093\u306a\u3084\u3064\u3067\u3082\u4f55\u8005\u304b\u306b\u306a\u308c\u308b\u3093\u3060 \u266b \u266b \u4e16\u754c\u3092\u5909\u3048\u3089\u308c\u308b\u3093\u3060 \u266b \u266b \u60f3\u50cf\u3057\u3066\u3054\u3089\u3093\u5b58\u5728\u4fa1\u5024\u3092\u611f\u3058\u308b\u4e16\u754c \u266b",
        "output": "\u266b Picture yourself in a world where there's no one else, \u266b \u266b nobody anywhere. \u266b \u266b A moment ago, there were voices and faces to look upon, \u266b \u266b you can't see them anywhere. \u266b \u266b Nothing more to say \u266b \u266b and no one left to say it to, anyway. \u266b \u266b Oh, listen to what I say. \u266b \u266b Everybody can be somebody \u266b \u266b and everybody is free to make a difference. \u266b \u266b Everybody can be somebody. \u266b \u266b Everybody is free to make a difference in this world. \u266b \u266b Now picture a world where the people all feel their worth. \u266b",
        "category": "Translation 341.json"
    },
    {
        "instruction": "You are given a sentence in Japanese. Your job is to translate the Japanese sentence into Spanish.",
        "input": "\u3053\u306e\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u306f\u3053\u308c\u3089\u4e09\u3064\u306e\u91cd\u5927\u306a\u554f\u984c\u306b\u53d6\u308a\u7d44\u3093\u3067\u3044\u308b\u306e\u3067\u3059\u3002\u305d\u308c\u3082\u3001\u79c1\u304c\u601d\u3046\u306b\u3001\u65ac\u65b0\u3067\u523a\u6fc0\u7684\u306a\u65b9\u6cd5\u3067\u3002",
        "output": "El proyecto entonces se dirige a estos temas centrales en una forma nueva y fascinante, yo creo.",
        "category": "Translation 342.json"
    },
    {
        "instruction": "You are given a sentence in Japanese. Your job is to translate the Japanese sentence into Arabic.",
        "input": "\u79c1\u306f\u5931\u8aad\u75c7\u3060\u3068\u8a00\u308f\u308c\u307e\u3057\u305f",
        "output": "\u0648\u0642\u062f \u062a\u0645 \u0625\u0639\u0644\u0627\u0645\u064a \u0628\u0623\u0646\u064a \u0645\u0635\u0627\u0628 \u0628\u0639\u0633\u0631 \u0627\u0644\u0642\u0631\u0627\u0621\u0629.",
        "category": "Translation 343.json"
    },
    {
        "instruction": "You are given a sentence in Japanese. Your job is to translate the Japanese sentence into Hebrew.",
        "input": "\u7d50\u5c40\u79c1\u306f\u5357\u30ab\u30ea\u30d5\u30a9\u30eb\u30cb\u30a2\u5927\u5b66\u30ed\u30fc\u30b9\u30af\u30fc\u30eb\u306e\u6559\u54e1\u3068\u3057\u3066\u30ed\u30b5\u30f3\u30bc\u30eb\u30b9\u306b\u6765\u308b\u3053\u3068\u306b\u306a\u308a\u307e\u3057\u305f",
        "output": "\u05d1\u05e1\u05d5\u05e4\u05d5 \u05e9\u05dc \u05d3\u05d1\u05e8 \u05d4\u05d2\u05e2\u05ea\u05d9 \u05dc\u05dc\u05d5\u05e1-\u05d0\u05e0\u05d2 '\u05dc\u05e1 \u05db\u05d3\u05d9 \u05dc\u05dc\u05de\u05d3 \u05d1\u05e4\u05e7\u05d5\u05dc\u05d8\u05d4 \u05dc\u05de\u05e9\u05e4\u05d8\u05d9\u05dd \u05e9\u05dc \u05d0\u05d5\u05e0' \u05d3\u05e8\u05d5\u05dd-\u05e7\u05dc\u05d9\u05e4\u05d5\u05e8\u05e0\u05d9\u05d4",
        "category": "Translation 344.json"
    },
    {
        "instruction": "You are given a sentence in Spanish. Your job is to translate the Spanish sentence into English.",
        "input": "Entonces el micelio se satur\u00f3 de petr\u00f3leo y cuando volvimos seis semanas despu\u00e9s se hab\u00edan eliminado todos los desechos, el resto de las pilas estaban muertas, oscuras, ol\u00edan mal.",
        "output": "So, the mycelium becomes saturated with the oil, and then, when we returned six weeks later, all the tarps were removed, all the other piles were dead, dark and stinky.",
        "category": "Translation 345.json"
    },
    {
        "instruction": "You are given a sentence in Spanish. Your job is to translate the Spanish sentence into Japanese.",
        "input": "Volviendo a 1976 \u2013",
        "output": "1976\u5e74\u306b\u3055\u304b\u623b\u308a\u307e\u3059",
        "category": "Translation 346.json"
    },
    {
        "instruction": "You are given a sentence in Spanish. Your job is to translate the Spanish sentence into Arabic.",
        "input": "Ese mes, entre el 20 de diciembre y finales de diciembre, su nombre fue googeleado 1 220 000 veces.",
        "output": "\u0641\u064a \u0630\u0627\u0643 \u0627\u0644\u0634\u0647\u0631 \u060c \u0645\u0646 20 \u062f\u064a\u0633\u0645\u0628\u0631 \u0625\u0644\u0649 \u0622\u062e\u0631 \u0627\u0644\u0634\u0647\u0631 \u062a\u0645 \u0627\u0644\u0628\u062d\u062b \u0639\u0646 \u0627\u0633\u0645\u0647\u0627 1.220.00 \u0645\u0631\u0629.",
        "category": "Translation 347.json"
    },
    {
        "instruction": "You are given a sentence in Spanish. Your job is to translate the Spanish sentence into Hebrew.",
        "input": "\u00bfQu\u00e9 tienen de malo las ciudades actuales?",
        "output": "\u05de\u05d4 \u05dc\u05d0 \u05d1\u05e1\u05d3\u05e8 \u05e2\u05dd \u05d4\u05e2\u05e8\u05d9\u05dd \u05e9\u05dc\u05e0\u05d5 \u05d4\u05d9\u05d5\u05dd?",
        "category": "Translation 348.json"
    },
    {
        "instruction": "In this task you will be given a list, of lists, of numbers. Each list is presented with brackets and comma-separated values. For example, a list of numbers is [1,2,3] and a list of two lists of numbers is [[1,2],[3,4,6]]. You should sum up the values at every position of every inner list and put it as an element of your answer, that is, you should sum the first members of each inner list together and put it as the first element of the list, then sum the second members of each inner list together and put it as the second element of your list, etc. The output should be a list of numbers with the same length as the longest inner list.",
        "input": "[[21, -20, 5, 88, -18, -29, 29], [-77, 82, -75, -57, -26, -90, -29, -36], [-65, -21, -16, 10, -86, 13, -71, 15], [90, -83, -58, -8, -49, -3, -25, -34, 39], [-1, -4, 64, 77, 68, -90, 71, 58, 2], [36, -60, 79], [-77, 68, -27, -24, 82, 47, 29]]",
        "output": "[-73, -38, -28, 86, -29, -152, 4, 3, 41]",
        "category": "Program Execution 349.json"
    },
    {
        "instruction": "You are given a sentence in Arabic. Your job is to translate the Arabic sentence into English.",
        "input": "\u0648 \u0644\u0645 \u0646\u0643\u0646 \u0646\u0639\u0644\u0645 \u0627\u0646 \u0627\u0644\u0627\u0633\u062a\u062e\u0628\u0627\u0631\u0627\u062a \u0627\u0644\u0645\u0631\u064a\u0643\u064a\u0629 \u062a\u062a\u062e\u0630 \u0645\u0648\u0627\u0642\u0641 \u0645\u062a\u0637\u0631\u0641 \u0645\u062b\u0644 \u0627\u0644\u062a\u0633\u0644\u0644 \u0644\u0647\u064a\u0626\u0627\u062a \u0627\u0644\u062a\u0642\u064a\u064a\u0633 \u0644\u062a\u062e\u0631\u064a\u0628 \u062e\u0648\u0627\u0631\u0632\u0645\u064a\u0627\u062a \u0627\u0644\u062a\u0634\u0641\u064a\u0631 \u0639\u0644\u0649 \u0627\u064a \u063a\u0631\u0636",
        "output": "And we did not know that U.S. intelligence agencies go to extremes such as infiltrating standardization bodies to sabotage encryption algorithms on purpose.",
        "category": "Translation 350.json"
    },
    {
        "instruction": "You are given a sentence in Arabic. Your job is to translate the Arabic sentence into Japanese.",
        "input": "\u0648\u0644\u0643\u0646 \u0631\u0628\u0645\u0627 \u0627\u0644\u0623\u0645\u0631 \u0644\u064a\u0633 \u0643\u0630\u0644\u0643.",
        "output": "\u3057\u304b\u3057\u304a\u305d\u3089\u304f\u73fe\u5b9f\u306f\u9055\u3044\u307e\u3059",
        "category": "Translation 351.json"
    },
    {
        "instruction": "You are given a sentence in Arabic. Your job is to translate the Arabic sentence into Spanish.",
        "input": "\u0647\u0646\u0627\u0643 \u0645\u0642\u0648\u0644\u0629 \u0639\u0638\u064a\u0645\u0629 \u0644\u0646\u064a\u0644 \u0633\u062a\u064a\u0641\u0646\u0633\u0648\u0646 \u062d\u064a\u062b \u064a\u0642\u0648\u0644 \u0639\u0644\u0649 \u0627\u0644\u0646\u0627\u0633 \u0627\u0644\u0645\u062a\u0635\u0644\u064a\u0646 \u0628\u0627\u0644\u0625\u0646\u062a\u0631\u0646\u062a \u0623\u0646 \u064a\u062a\u0639\u0644\u0645\u0648\u0627 \u0634\u064a\u0621 \u0639\u0646 \u0627\u0644\u0623\u0633\u0644\u0627\u0643.",
        "output": "Hay una excelente frase de Neal Stephenson en la que dice que las personas conectadas deber\u00edan saber algo acerca de cables.",
        "category": "Translation 352.json"
    },
    {
        "instruction": "You are given a sentence in Arabic. Your job is to translate the Arabic sentence into Hebrew.",
        "input": "\u0648\u0642\u062f \u062c\u0626\u062a \u0627\u0644\u0649 \u0647\u0646\u0627 \u0644\u0643 \u0627\u062a\u062d\u062f\u062b \u0639\u0645\u0627 \u064a\u0639\u064a\u0628 \u0646\u0638\u0627\u0645\u0646\u0627 \u0627\u0644\u063a\u0630\u0627\u0626\u064a",
        "output": "\u05d1\u05d0\u05ea\u05d9 \u05dc\u05db\u05d0\u05df \u05d4\u05d9\u05d5\u05dd \u05db\u05d3\u05d9 \u05dc\u05e1\u05e4\u05e8 \u05de\u05d4 \u05dc\u05d0 \u05d1\u05e1\u05d3\u05e8 \u05d1\u05de\u05e2\u05e8\u05db\u05ea \u05d4\u05de\u05d6\u05d5\u05df \u05e9\u05dc\u05e0\u05d5.",
        "category": "Translation 353.json"
    },
    {
        "instruction": "You are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into English.",
        "input": "\u05d0\u05d6 \u05e6\u05e8\u05d9\u05da \u05dc\u05d8\u05e4\u05dc \u05d1\u05de\u05d9\u05d3\u05e2 \u05d4\u05de\u05d5\u05d8\u05e2\u05d4 \u05d4\u05d6\u05d4, \u05d1\u05e4\u05e2\u05e8 \u05d1\u05d9\u05df \u05ea\u05e4\u05d9\u05e1\u05d4 \u05d5\u05de\u05e6\u05d9\u05d0\u05d5\u05ea \u05e2\u05dc \u05d4\u05d9\u05d1\u05d8\u05d9\u05dd \u05d7\u05e9\u05d5\u05d1\u05d9\u05dd \u05e9\u05dc \u05d2\u05dc\u05d5\u05d1\u05dc\u05d9\u05d6\u05e6\u05d9\u05d4.",
        "output": "So we have to address this misinformation, the gap between perception and reality on key aspects of globalization.",
        "category": "Translation 354.json"
    },
    {
        "instruction": "You are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into Japanese.",
        "input": "\u05d5\u05d4\u05d2\u05e0\u05d1\u05ea\u05d9 \u05ea\u05e4\u05e8\u05d9\u05d8 \u05dc\u05de\u05db\u05e0\u05e1\u05d9\u05d9\u05dd \u05e9\u05dc\u05d9.",
        "output": "\u30ba\u30dc\u30f3\u306e\u4e2d\u306b\u30e1\u30cb\u30e5\u30fc\u3092\u96a0\u3057\u3066\u6301\u3061\u5e30\u308a\u3082\u3057\u307e\u3057\u305f",
        "category": "Translation 355.json"
    },
    {
        "instruction": "You are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into Spanish.",
        "input": "\u05d5\u05db\u05e9\u05d0\u05e0\u05d5 \u05de\u05ea\u05d9\u05dd, \u05dc\u05d0 \u05e6\u05e8\u05d9\u05da \u05d0\u05e4\u05d9\u05dc\u05d5 \u05dc\u05e9\u05d9\u05dd \u05d0\u05d5\u05ea\u05e0\u05d5 \u05d1\u05e9\u05e7\u05d9 \u05d0\u05e9\u05e4\u05d4 \u05e0\u05e4\u05e8\u05d3\u05d9\u05dd.",
        "output": "Y cuando morimos, ni siquiera se nos tiene que colocar en bolsas de residuos diferentes.",
        "category": "Translation 356.json"
    },
    {
        "instruction": "You are given a sentence in Hebrew. Your job is to translate the Hebrew sentence into Arabic.",
        "input": "\u05d0\u05d1\u05dc \u05de\u05d4 \u05e9\u05d1\u05d0\u05de\u05ea \u05de\u05e2\u05e0\u05d9\u05d9\u05df \u05d0\u05d5\u05ea\u05d9, \u05d1\u05de\u05d9\u05d5\u05d7\u05d3 \u05d1\u05d9\u05de\u05d9\u05dd \u05d0\u05dc\u05d4 \u05d5\u05d1\u05d2\u05dc\u05dc \u05de\u05d4 \u05e9\u05e7\u05d5\u05e8\u05d4 \u05de\u05d1\u05d7\u05d9\u05e0\u05d4 \u05e4\u05d5\u05dc\u05d9\u05d8\u05d9\u05ea \u05de\u05e1\u05d1\u05d9\u05d1 \u05dc\u05e2\u05d5\u05dc\u05dd, \u05d6\u05d5 \u05d4\u05e9\u05e4\u05d4 \u05d1\u05d4 \u05de\u05e9\u05ea\u05de\u05e9\u05d9\u05dd, \u05d4\u05e0\u05e8\u05d8\u05d9\u05d1, \u05d4\u05e9\u05d9\u05d7, \u05d4\u05d3\u05d9\u05de\u05d5\u05d9\u05d9\u05dd, \u05d4\u05de\u05d9\u05dc\u05d9\u05dd \u05e2\u05e6\u05de\u05df.",
        "output": "\u0648\u0644\u0643\u0646 \u0645\u0627\u064a\u062b\u064a\u0631 \u0627\u0647\u062a\u0645\u0627\u0645\u064a \u062d\u0642\u0627\u064b \u060c \u0644\u0627 \u0633\u064a\u0645\u0627 \u0641\u064a \u0627\u0644\u0648\u0642\u062a \u0627\u0644\u062d\u0627\u0636\u0631 \u0628\u0627\u0644\u0646\u0638\u0631 \u0644\u0645\u0627 \u064a\u062d\u062f\u062b \u0633\u064a\u0627\u0633\u064a\u0627\u064b \u062d\u0648\u0644 \u0627\u0644\u0639\u0627\u0644\u0645 \u060c \u0647\u064a \u0627\u0644\u0644\u063a\u0629 \u0627\u0644\u0645\u0633\u062a\u062e\u062f\u0645\u0629 \u060c \u0627\u0644\u0633\u0631\u062f \u060c \u0627\u0644\u062e\u0637\u0627\u0628 \u060c \u0627\u0644\u0635\u0648\u0631 \u060c \u0627\u0644\u0643\u0644\u0645\u0627\u062a \u0627\u0644\u0641\u0639\u0644\u064a\u0629.",
        "category": "Translation 357.json"
    },
    {
        "instruction": "You are given a sentence in Galician. Your job is to translate the Galician sentence into English.",
        "input": "Esta aspiraci\u00f3n \u00e9 enormemente poderosa.",
        "output": "This aspiration that our healthcare keep us healthy is an enormously powerful one.",
        "category": "Translation 358.json"
    },
    {
        "instruction": "You are given a sentence in Galician. Your job is to translate the Galician sentence into Japanese.",
        "input": "Vemos maz\u00e1s vermellas, amarelas e verdes, e non hai m\u00e1is.",
        "output": "\u308a\u3093\u3054\u306b\u3057\u3066\u3082\u8d64\u3044\u3082\u306e\u3001\u9ec4\u8272\u306e\u3082\u306e\u3001\u7dd1\u306e\u3082\u306e\u304c\u7f6e\u3044\u3066\u3042\u308b\u3060\u3051\u3067\u3059\u3002",
        "category": "Translation 359.json"
    },
    {
        "instruction": "Write a fact related to the given fact, based on the given topic word. Note that, your fact should have at least one word in common with the given fact. All facts in this task refer to scientific facts. Your related fact must form a chain with the given fact. Chains form when two facts connect together to produce the third fact. An example of a chain is: \"pesticides cause pollution\" (given fact) + \"pollution can harm animals\" (related fact) \u2192 \"pesticides can harm animals\" (connected chain). Avoid creating simple paraphrases of the given fact. While your generated fact should be related to the input fact, they must describe slightly different scientific phenomena. It's okay if your related fact includes some irrelevant information, provided that it has some overlap with the given fact and it contains some words corresponding to the provided topic.",
        "input": "Fact: Energy enters ecosystems in the form of sunlight or chemical compounds. \nTopic: energy enters ecosystems.",
        "output": "Energy flow in an ecosystem is one way.",
        "category": "Sentence Composition 36.json"
    },
    {
        "instruction": "In this task you will be given a list of dictionaries. A dictionary is a set of key-value pairs, where each key is unique and has a value associated with that key. You should sort the list of dictionaries from smallest to largest by their 'first' key. If there is two dictionaries with the same 'first' value then sort them by their 'second' key. Negative numbers should come before positive numbers.",
        "input": "[{'first': 46, 'second': 45}, {'first': -39, 'second': 10}, {'first': 2, 'second': -99}, {'first': 72, 'second': -33}, {'first': -55, 'second': 46}, {'first': -60, 'second': -68}, {'first': 95, 'second': 40}, {'first': 31, 'second': 7}]",
        "output": "[{'first': -60, 'second': -68}, {'first': -55, 'second': 46}, {'first': -39, 'second': 10}, {'first': 2, 'second': -99}, {'first': 31, 'second': 7}, {'first': 46, 'second': 45}, {'first': 72, 'second': -33}, {'first': 95, 'second': 40}]",
        "category": "Program Execution 360.json"
    },
    {
        "instruction": "You are given a sentence in Galician. Your job is to translate the Galician sentence into Spanish.",
        "input": "N\u00famero cinco: Se non saben, digan que non saben.",
        "output": "N\u00famero cinco: Si no saben, digan que no lo saben.",
        "category": "Translation 361.json"
    },
    {
        "instruction": "You are given a sentence in Galician. Your job is to translate the Galician sentence into Arabic.",
        "input": "O \u00fanico que pode reducir a cantidade de petr\u00f3leo que consumimos \u00e9 incrementar os prezos.",
        "output": "\u0627\u0644\u0634\u064a\u0621 \u0627\u0644\u0648\u062d\u064a\u062f \u0627\u0644\u0630\u064a \u064a\u0642\u0644\u0644 \u0645\u0646 \u0627\u0633\u062a\u0647\u0644\u0627\u0643\u0646\u0627 \u0644\u0644\u0646\u0641\u0637 \u062d\u0642\u064a\u0642\u0629 \u0647\u0648 \u0627\u0644\u0632\u064a\u0627\u062f\u0629 \u0641\u064a \u0627\u0644\u0623\u0633\u0639\u0627\u0631",
        "category": "Translation 362.json"
    },
    {
        "instruction": "You are given a sentence in Galician. Your job is to translate the Galician sentence into Hebrew.",
        "input": "Agora entendemos que todas as bacterias falan unhas con outras.",
        "output": "\u05db\u05dc\u05d5\u05de\u05e8, \u05db\u05dc \u05d4\u05d7\u05d9\u05d9\u05d3\u05e7\u05d9\u05dd \u05d9\u05db\u05d5\u05dc\u05d9\u05dd \u05dc\u05e9\u05d5\u05d7\u05d7 \u05d6\u05d4 \u05e2\u05dd \u05d6\u05d4.",
        "category": "Translation 363.json"
    },
    {
        "instruction": "You are given a sentence in Galician. Your job is to translate the Galician sentence into Italian.",
        "input": "Cada ano damos 10 premios.",
        "output": "Ogni anno conferiamo dieci premi.",
        "category": "Translation 364.json"
    },
    {
        "instruction": "You are given a sentence in Galician. Your job is to translate the Galician sentence into Polish.",
        "input": "Quero tratar o tema da compaix\u00f3n.",
        "output": "Chc\u0119 zaj\u0105\u0107 si\u0119 kwesti\u0105 wsp\u00f3\u0142czucia,",
        "category": "Translation 365.json"
    },
    {
        "instruction": "You are given a sentence in Galician. Your job is to translate the Galician sentence into Farsi.",
        "input": "Primeiro, collemos o relato e reproduc\u00edmolo ao rev\u00e9s.",
        "output": "\u0627\u0648\u0644 \u060c \u0645\u0627 \u062f\u0627\u0633\u062a\u0627\u0646 \u0631\u0627 \u0628\u0631\u062f\u0627\u0634\u062a\u06cc\u0645 \u0648 \u0628\u0631\u0639\u06a9\u0633 \u067e\u062e\u0634 \u06a9\u0631\u062f\u06cc\u0645.",
        "category": "Translation 366.json"
    },
    {
        "instruction": "You are given a sentence in Italian. Your job is to translate the Italian sentence into English.",
        "input": "Pu\u00f2 seguire i gradienti chimici.",
        "output": "It can follow chemical gradients.",
        "category": "Translation 368.json"
    },
    {
        "instruction": "You are given a sentence in Italian. Your job is to translate the Italian sentence into Japanese.",
        "input": "WISER vuole documentare, collegare e dare potere a quello che Paul chiama il pi\u00f9 grande e veloce movimento in crescita nella storia umana. La risposta immunologica collettiva dell'umanit\u00e0 alle minacce di oggi.",
        "output": "WISER\u306f\u4eba\u985e\u53f2\u4e0a\u304b\u3064\u3066\u306a\u3044\u30b9\u30b1\u30fc\u30eb\u3068\u30b9\u30d4\u30fc\u30c9\u306e\u3053\u3046\u3057\u305f\u52d5\u304d\u3092\u6587\u66f8\u5316\u3057\u305d\u3057\u3066\u30ea\u30f3\u30af\u3057\u3066\u52a0\u901f\u3055\u305b\u3088\u3046\u3068\u3057\u3066\u3044\u307e\u3059\u4eca\u65e5\u306e\u8105\u5a01\u306b\u5bfe\u3059\u308b\u4eba\u985e\u306e\u96c6\u5408\u7684\u306a\u6297\u4f53\u3068\u8a00\u3048\u307e\u3059",
        "category": "Translation 369.json"
    },
    {
        "instruction": "Combine the given two facts to write a concluding fact. Note that there should be some parts of the first and second facts that are not mentioned in this conclusion fact. Your combined fact should be the result of a chain between the two facts. Chains form when two facts connect together to produce a concluding fact. An example of a chain is: \"pesticides cause pollution\" (fact1) + \"pollution can harm animals\" (fact2) \u2192 \"pesticides can harm animals\" (conclusion fact). Parts of the concluding fact overlap with the first and the second fact. To construct such a  concluding fact, a useful way is to borrow the subject from one fact and the ending conclusions from another fact.",
        "input": "Fact 1: Fish have a circulatory system with a two-chambered heart. \nFact 2: Each side of the heart is divided up into two chambers.",
        "output": "Fish have a circulatory system with a heart that is divided.",
        "category": "Sentence Composition 37.json"
    },
    {
        "instruction": "You are given a sentence in Italian. Your job is to translate the Italian sentence into Spanish.",
        "input": "A volte, non possiamo risolvere i grandi problemi perch\u00e9 il nostro sistema politico fallisce.",
        "output": "A veces, no podemos solucionar los grandes problemas porque los sistemas pol\u00edticos fallan.",
        "category": "Translation 370.json"
    },
    {
        "instruction": "In this task you are given a list of numbers and you need to find the average of each two consecutive values. The average of two numbers a and b is calculated as: (a + b) /2. The output should be a list of the averages of each two consecutive values. A list is presented with two brackets and comma-separated values, like: [1,2,3].",
        "input": "[90, -88, 90]",
        "output": "[1.0, 1.0]",
        "category": "Program Execution 371.json"
    },
    {
        "instruction": "You are given a sentence in Italian. Your job is to translate the Italian sentence into Arabic.",
        "input": "Di giorno saltano sui treni merci, e con i loro pollici alzati viaggiano lungo le autostrade con chi capita, da camionisti a madri di famiglia.",
        "output": "\u0641\u064a \u0627\u0644\u0646\u0647\u0627\u0631 \u060c \u064a\u0642\u0641\u0632\u0648\u0646 \u0639\u0644\u0649 \u0627\u0644\u0642\u0637\u0627\u0631\u0627\u062a \u060c \u064a\u0624\u0634\u0631\u0648\u0646 \u0628\u0625\u0628\u0647\u0627\u0645\u0647\u0645 \u060c \u0648\u064a\u0631\u0643\u0628\u0648\u0646 \u0627\u0644\u0637\u0631\u0642\u0627\u062a \u0627\u0644\u0633\u0631\u064a\u0639\u0629 \u0645\u0639 \u0623\u064a \u0643\u0627\u0646 \u0645\u0646 \u0642\u0627\u0626\u062f\u064a \u0627\u0644\u0634\u0627\u062d\u0627\u0646\u0627\u062a \u0625\u0644\u0649 \u0623\u0645\u0647\u0627\u062a \u0627\u0644\u0636\u0648\u0627\u062d\u064a.",
        "category": "Translation 372.json"
    },
    {
        "instruction": "You are given a sentence in Italian. Your job is to translate the Italian sentence into Hebrew.",
        "input": "(Risate) E ogni anno si fanno delle ricerche tra gli studenti universitari sulla timidezza autoproclamata.",
        "output": "(\u05e6\u05d7\u05d5\u05e7) \u05d5\u05db\u05dc \u05e9\u05e0\u05d4 \u05e0\u05e2\u05e8\u05da \u05de\u05d7\u05e7\u05e8 \u05e2\u05dc \u05d1\u05d9\u05d9\u05e9\u05e0\u05d5\u05ea \u05de\u05d3\u05d5\u05d5\u05d7\u05ea \u05e2\u05e6\u05de\u05d0\u05d9\u05ea \u05d1\u05ea\u05dc\u05de\u05d9\u05d3\u05d9 \u05e7\u05d5\u05dc\u05d2 '",
        "category": "Translation 373.json"
    },
    {
        "instruction": "You are given a sentence in Italian. Your job is to translate the Italian sentence into Galician.",
        "input": "E noi, e io, e noi siamo tutti parte di te.",
        "output": "E n\u00f3s, e eu, e todos n\u00f3s somos parte t\u00faa.",
        "category": "Translation 374.json"
    },
    {
        "instruction": "You are given a sentence in Italian. Your job is to translate the Italian sentence into Polish.",
        "input": "La pi\u00f9 grande societ\u00e0 mineraria sulle montagne \u00e8 Massey Coal. Questo \u00e8 il suo amministratore.",
        "output": "Najwa\u017cniejszym z g\u00f3rnik\u00f3w jest dyrektor Massey Coal.",
        "category": "Translation 375.json"
    },
    {
        "instruction": "You are given a sentence in Italian. Your job is to translate the Italian sentence into Farsi.",
        "input": "\u00c8 seguita dai suoi quattro figli, tutti uccisi nel massacro di Srebrenica.",
        "output": "\u0639\u06a9\u0633\u0647\u0627\u06cc \u0628\u0639\u062f\u06cc \u060c \u0686\u0647\u0627\u0631 \u0641\u0631\u0632\u0646\u062f \u0627\u0648\u0633\u062a \u06a9\u0647 \u0647\u0645\u06af\u06cc \u062a\u0648\u0633\u0637 \u0635\u0631\u0628\u0647\u0627 \u0642\u062a\u0644 \u0639\u0627\u0645 \u0634\u062f\u0646\u062f",
        "category": "Translation 376.json"
    },
    {
        "instruction": "You are given a sentence in Italian. Your job is to translate the Italian sentence into Portugese.",
        "input": "A volte potremmo scoprire che non ci prendiamo cura di noi stessi.",
        "output": "\u00c0 vezes podemos descobrir que n\u00e3o temos cuidado com n\u00f3s pr\u00f3prios.",
        "category": "Translation 377.json"
    },
    {
        "instruction": "You are given a sentence in Polish. Your job is to translate the Polish sentence into English.",
        "input": "Doje\u017cd\u017ca\u0142am do szko\u0142y autobusem na przedmie\u015bcia z dzielnicy, kt\u00f3r\u0105 wielu moich koleg\u00f3w z klasy i ich rodzic\u00f3w uwa\u017ca\u0142o za niebezpieczn\u0105.",
        "output": "I was bussed to a school in the suburbs, from a neighborhood that many of my classmates and their parents considered dangerous.",
        "category": "Translation 378.json"
    },
    {
        "instruction": "You are given a sentence in Polish. Your job is to translate the Polish sentence into Japanese.",
        "input": "Na kr\u00f3tk\u0105 met\u0119 idzie si\u0119 w g\u00f3r\u0119 a potem, na d\u0142u\u017csz\u0105 met\u0119, idzie si\u0119 jeszcze bardziej w g\u00f3r\u0119.",
        "output": "\u77ed\u671f\u7684\u306b\u6210\u9577\u3057\u305d\u3057\u3066\u9577\u671f\u7684\u306b\u306f\u3055\u3089\u306a\u308b\u6210\u9577\u3092\u3068\u3052\u307e\u3059",
        "category": "Translation 379.json"
    },
    {
        "instruction": "Generate an overlapping word between the given two sentences. When you find the overlapping words, they don't have to match exactly, e.g., \"survival\" and \"survive\" are valid overlapping words. Little words like \"the\" or \"of\" don't count! You must generate significant words which are not the stop words.",
        "input": "Sentence1: Fertilization is the penetration of the egg by a sperm. \nSentence2: Sperm must swim from the male to the female egg.",
        "output": "egg",
        "category": "Overlap Extraction 38.json"
    },
    {
        "instruction": "You are given a sentence in Polish. Your job is to translate the Polish sentence into Spanish.",
        "input": "A to jest tr\u00f3jk\u0105t \u0142\u0105cz\u0105cy Salk, Scripps i UCSD. Nazywa si\u0119 Torrey Pines Road.",
        "output": "Y eso es el tri\u00e1ngulo entre las calles Sulk, Scripps, UCSD, y se llama Torrey Pines Road.",
        "category": "Translation 380.json"
    },
    {
        "instruction": "You are given a sentence in Polish. Your job is to translate the Polish sentence into Arabic.",
        "input": "Przecie\u017c jeste\u015bmy szale\u0144cami zabieraj\u0105cymi si\u0119 za niemo\u017cliwe zadanie.",
        "output": "\u0628\u0645\u0627 \u0623\u0646\u0646\u0627 \u0623\u0634\u062e\u0627\u0635 \u0645\u062c\u0627\u0646\u064a\u0646 \u0646\u062d\u0627\u0648\u0644 \u062a\u0646\u0641\u064a\u0630 \u0645\u0647\u0645\u0629 \u0645\u0633\u062a\u062d\u064a\u0644\u0629",
        "category": "Translation 381.json"
    },
    {
        "instruction": "In this task you are given a list of integers and you need to find the absolute value of the difference between each two consecutive values. The output should be a list of the absolute value of the differences of each two consecutive values.",
        "input": "[-35, -9, 94]",
        "output": "[26, 103]",
        "category": "Program Execution 382.json"
    },
    {
        "instruction": "You are given a sentence in Polish. Your job is to translate the Polish sentence into Hebrew.",
        "input": "S\u0105d dla Weteran\u00f3w traktowa\u0142 ka\u017cdy przypadek jako wyj\u0105tkowy, stara\u0142 si\u0119 dotrze\u0107 do sedna problem\u00f3w, dopasowa\u0107 do pope\u0142nionych przest\u0119pstw co pomaga\u0142o si\u0119 im zrehabilitowa\u0107 i nie zapomina\u0142 o nich po wydaniu wyroku.",
        "output": "\u05d5\u05de\u05d4 \u05e9\u05e2\u05e9\u05d4 \u05d1\u05d9\u05ea-\u05d4\u05de\u05e9\u05e4\u05d8 \u05dc\u05d9\u05d5\u05e6\u05d0\u05d9-\u05e6\u05d1\u05d0, \u05e9\u05d4\u05d5\u05d0 \u05d4\u05ea\u05d9\u05d7\u05e1 \u05dc\u05db\u05dc \u05e2\u05d1\u05e8\u05d9\u05d9\u05df \u05d1\u05d0\u05d5\u05e4\u05df \u05d0\u05d9\u05e9\u05d9, \u05e0\u05d9\u05e1\u05d4 \u05dc\u05d7\u05d3\u05d5\u05e8 \u05d0\u05dc \u05ea\u05d5\u05da \u05d1\u05e2\u05d9\u05d5\u05ea\u05d9\u05d4\u05dd, \u05e0\u05d9\u05e1\u05d4 \u05dc\u05ea\u05e4\u05d5\u05e8 \u05ea\u05e9\u05d5\u05d1\u05d5\u05ea \u05dc\u05e4\u05d9 \u05e4\u05e9\u05e2\u05d9\u05d4\u05dd, \u05d3\u05d1\u05e8 \u05e9\u05e1\u05d9\u05d9\u05e2 \u05dc\u05d4\u05dd \u05dc\u05d4\u05e9\u05ea\u05e7\u05dd, \u05d5\u05dc\u05d0 \u05e9\u05db\u05d7 \u05d0\u05d5\u05ea\u05dd \u05e8\u05d2\u05e2 \u05dc\u05d0\u05d7\u05e8 \u05e9\u05d4\u05dd \u05e0\u05e9\u05e4\u05d8\u05d5.",
        "category": "Translation 383.json"
    },
    {
        "instruction": "You are given a sentence in Polish. Your job is to translate the Polish sentence into Galician.",
        "input": "Jak z \"\" Willy Wonka i Fabryka Czekolady \"\". To by\u0142o niesamowite.",
        "output": "Era como. Foi incrible.",
        "category": "Translation 384.json"
    },
    {
        "instruction": "You are given a sentence in Polish. Your job is to translate the Polish sentence into Italian.",
        "input": "Robotnica musi rozumie\u0107 r\u00f3\u017cnic\u0119 pomi\u0119dzy mr\u00f3wkami wykonuj\u0105cymi poszczeg\u00f3lne zadania.",
        "output": "Quindi deve conoscere la differenza tra una raccoglitrice ed una della squadra manutenzione nido.",
        "category": "Translation 385.json"
    },
    {
        "instruction": "You are given a sentence in Polish. Your job is to translate the Polish sentence into Farsi.",
        "input": "Ale m\u00f3j robot, STriDER, nie porusza si\u0119 w ten spos\u00f3b.",
        "output": "\u0627\u0645\u0627 \u0631\u0648\u0628\u0627\u062a \u0645\u0646 \u060c \u0627\u0650\u0633\u062a\u0631\u06cc\u062f\u0650\u0631 \u060c \u0627\u06cc\u0646 \u0637\u0648\u0631\u06cc \u062d\u0631\u06a9\u062a \u0646\u0645\u06cc \u200c \u06a9\u0646\u062f.",
        "category": "Translation 386.json"
    },
    {
        "instruction": "You are given a sentence in Polish. Your job is to translate the Polish sentence into Portugese.",
        "input": "Mamy ponad stu t\u0142umaczy t\u0142umacz\u0105cych w 63 j\u0119zykach, i tylko w naszym ma\u0142ym szpitalu wydajemy na to miliony dolar\u00f3w.",
        "output": "Temos mais de 100 tradutores cobrindo 63 l\u00ednguas e gastamos milh\u00f5es de d\u00f3lares apenas no nosso pequeno hospital.",
        "category": "Translation 387.json"
    },
    {
        "instruction": "You are given a sentence in Persian. Your job is to translate the Farsi sentence into English.",
        "input": "(\u062e\u0646\u062f\u0647 \u06cc \u062d\u0627\u0636\u0631\u06cc\u0646) \u062f\u0631\u0633\u062a \u0627\u0633\u062a \u061f",
        "output": "(Laughter) Right?",
        "category": "Translation 388.json"
    },
    {
        "instruction": "You are given a sentence in Persian. Your job is to translate the Farsi sentence into Japanese.",
        "input": "\u0628\u0646\u0627\u0628\u0631\u0627\u06cc\u0646 \u0648\u0642\u062a\u06cc \u0634\u0645\u0627 \u06a9\u0644\u0645\u0627\u062a \"\" \u0633\u0628\u06a9 \u0632\u0646\u062f\u06af\u06cc \u0647\u0645\u062c\u0646\u0633 \u06af\u0631\u0627\u06cc\u06cc \"\" \u0648 \"\" \u0622\u06cc\u06cc\u0646 \u0646\u0627\u0645\u0647 \u06cc \u0647\u0645\u062c\u0646\u0633 \u06af\u0631\u0627\u06cc\u06cc \"\" \u0631\u0627 \u062f\u0631 \u0622\u06cc\u0646\u062f\u0647 \u0645\u06cc \u0634\u0646\u0648\u06cc\u062f \u060c \u0634\u0645\u0627 \u0631\u0627 \u0628\u0647 \u062f\u0648 \u0645\u0648\u0631\u062f \u062a\u0634\u0648\u06cc\u0642 \u0645\u06cc \u06a9\u0646\u0645: \u0627\u0648\u0644 \u060c \u062d\u0642\u0648\u0642 \u0634\u0647\u0631\u0648\u0646\u062f\u06cc \u0627\u06cc\u0627\u0644\u0627\u062a \u0645\u062a\u062d\u062f\u0647 \u0631\u0627 \u0628\u0647 \u06cc\u0627\u062f \u0628\u06cc\u0627\u0648\u0631\u06cc\u062f \u060c \u0648 \u062f\u0648\u0645 \u060c \u0627\u06af\u0631 \u0645\u0645\u06a9\u0646 \u0627\u0633\u062a \u0628\u0647 \u0633\u0645\u062a \u0686\u067e \u062e\u0648\u062f \u0646\u06af\u0627\u0647 \u06a9\u0646\u06cc\u062f \u060c \u0644\u0637\u0641\u0627.",
        "output": "\u4eca\u5ea6\u7686\u3055\u3093\u304c\u300c\u30b2\u30a4\u306e\u30e9\u30a4\u30d5\u30b9\u30bf\u30a4\u30eb\u300d\u3068\u304b\u300c\u30b2\u30a4\u30a2\u30b8\u30a7\u30f3\u30c0\u300d\u3068\u304b\u3044\u3046\u8a00\u8449\u3092\u8033\u306b\u3057\u305f\u3089 \uff12\u3064\u306e\u4e8b\u3092\u3084\u3063\u3066\u307f\u3066\u4e0b\u3055\u3044\u307e\u305a\u5408\u8846\u56fd\u61b2\u6cd5\u3092\u601d\u3044\u51fa\u3057\u3066\u4e0b\u3055\u3044\u6b21\u306b\u5de6\u5074\u3092\u898b\u3066\u3082\u3089\u3048\u307e\u3059\u304b \uff1f",
        "category": "Translation 389.json"
    },
    {
        "instruction": "Turn the given fact into a question by a simple rearrangement of words. This typically involves replacing some part of the given fact with a WH word. For example, replacing the subject of the provided fact with the word \"what\" can form a valid question. Don't be creative! You just need to rearrange the words to turn the fact into a question - easy! Don't just randomly remove a word from the given fact to form a question. Remember that your question must evaluate scientific understanding. Pick a word or a phrase in the given fact to be the correct answer, then make the rest of the question. You can also form a question without any WH words. For example, \"A radio converts electricity into?\"",
        "input": "Fact: bushes have specialized reproductive organs.",
        "output": "what have specialized reproductive organs?",
        "category": "Question Generation 39.json"
    },
    {
        "instruction": "You are given a sentence in Persian. Your job is to translate the Farsi sentence into Spanish.",
        "input": "\u0645\u0646 \u0645\u0627\u06cc\u0644\u0645 \u0622\u0647\u0646\u06af \u0628\u0639\u062f\u06cc \u0631\u0648 \u0628\u0647 \u06a9\u0627\u0631\u0645\u0644\u0648 \u062a\u0642\u062f\u06cc\u0645 \u06a9\u0646\u0645 \u060c \u06a9\u0647 \u062f\u0648 \u0631\u0648\u0632 \u067e\u06cc\u0634 \u062f\u0631\u06af\u0630\u0634\u062a \u0686\u0648\u0646 \u062e\u06cc\u0644\u06cc \u067e\u06cc\u0631 \u0628\u0648\u062f.",
        "output": "Me gustar\u00eda dedicar la siguiente canci\u00f3n a Carmelo. al que sacrificaron hace un par de d\u00edas porque se hizo demasiado viejo.",
        "category": "Translation 390.json"
    },
    {
        "instruction": "You are given a sentence in Persian. Your job is to translate the Farsi sentence into Arabic.",
        "input": "\u0648 \u062f\u0631 \u067e\u0627\u06cc\u0627\u0646 \u060c \u0627\u063a\u0644\u0628 \u0627\u0648\u0642\u0627\u062a \u060c \u0627\u06cc\u0646 \u0645\u06cc\u0644 \u0648 \u0647\u0648\u0633 \u060c \u0642\u0648\u06cc \u062a\u0631 \u0627\u0632 \u0622\u0646\u0647\u0627\u0633\u062a \u0648 \u0628\u0627\u0644\u0627\u062e\u0631\u0647 \u0646\u0627\u06af\u0647\u0627\u0646 \u0622\u0646 \u0631\u0627 \u0628\u0631\u0648\u0632 \u0645\u06cc \u200c \u062f\u0647\u0646\u062f: \u00ab \u0627\u06af\u0631 \u062a\u0627\u0631\u06cc\u062e \u062a\u0648\u0644\u062f\u0645 \u0631\u0627 \u0628\u062f\u0647\u0645 \u060c \u0645\u06cc \u200c \u062a\u0648\u0627\u0646\u06cc \u0628\u0647 \u0645\u0646 \u0628\u06af\u0648\u06cc\u06cc \u0686\u0647 \u0631\u0648\u0632\u06cc \u0627\u0632 \u0647\u0641\u062a\u0647 \u0628\u0647 \u062f\u0646\u06cc\u0627 \u0622\u0645\u062f\u0647 \u200c \u0627\u0645 \u061f \u00bb (\u062e\u0646\u062f\u0647 \u062a\u0645\u0627\u0634\u0627\u06af\u0631\u0627\u0646) \u06cc\u0627 \u0622\u0646\u0647\u0627 \u0631\u06cc\u0634\u06c0 \u0633\u0648\u0645 \u0631\u0627 \u0645\u0637\u0631\u062d \u0645\u06cc \u200c \u06a9\u0646\u0646\u062f \u06cc\u0627 \u0627\u0632 \u0645\u0646 \u0645\u06cc \u200c \u062e\u0648\u0627\u0647\u0646\u062f \u06cc\u06a9 \u0639\u062f\u062f \u0628\u0632\u0631\u06af \u06cc\u0627 \u06cc\u06a9 \u0646\u0648\u0634\u062a\u06c0 \u0637\u0648\u0644\u0627\u0646\u06cc \u0631\u0627 \u0627\u0632 \u0628\u0631 \u0628\u062e\u0648\u0627\u0646\u0645.",
        "output": "\u0648\u0641\u064a \u0627\u0644\u0646\u0647\u0627\u064a\u0629.. \u063a\u0627\u0644\u0628\u0627\u064b \u0645\u0627 \u064a\u0646\u062a\u0635\u0631 \u0635\u0631\u0627\u0639\u0647\u0645 \u0627\u0644\u062f\u0627\u062e\u0644\u064a \u0648\u064a\u062a\u063a\u0644\u0628 \u0639\u0644\u064a\u0647\u0645 \u0627\u0644\u0641\u0636\u0648\u0644 \u0641\u064a\u0637\u0631\u062d\u0648\u0646 \u0639\u062f\u0629 \u062a\u0633\u0627\u0624\u0644\u0627\u062a.. \u0645\u0646 \u0645\u062b\u0644.. \"\" \u0625\u0646 \u0623\u062e\u0628\u0631\u062a\u0643 \u0641\u064a \u0623\u064a \u062a\u0627\u0631\u064a\u062e \u0648\u0644\u062f\u062a.. \u0647\u0644 \u064a\u0645\u0643\u0646\u0643 \u0627\u0646 \u062a\u062e\u0628\u0631\u0646\u064a \u0641\u064a \u0623\u064a \u064a\u0648\u0645 \u0645\u0646 \u0627\u0644\u0627\u0633\u0628\u0648\u0639 \u0648\u0644\u062f\u062a \u061f \"\" (\u0636\u062d\u0643) \u0648\u0623\u062d\u064a\u0627\u0646\u0627 \u064a\u062a\u0633\u0627\u0626\u0644\u0648\u0646 \u0639\u0646 \u0627\u0644\u062c\u0630\u0648\u0631 \u0627\u0644\u0645\u0643\u0639\u0628\u064a\u0629 \u0627\u0648 \u064a\u0637\u0644\u0628\u0648\u0646 \u0645\u0646\u064a \u0623\u0646 \u0623\u0642\u0631\u0623 \u0631\u0642\u0645 \u0637\u0648\u064a\u0644.. \u0627\u0648 \u0639\u0628\u0627\u0631\u0629 \u0637\u0648\u064a\u0644\u0629",
        "category": "Translation 391.json"
    },
    {
        "instruction": "You are given a sentence in Persian. Your job is to translate the Farsi sentence into Hebrew.",
        "input": "\u0648 \u0627\u0648\u0646 \u0627\u0644\u0627\u0646 \u062f\u0631 \u062f\u0647\u0647 \u0647\u0634\u062a\u0645 \u0632\u0646\u062f\u06af\u064a\u0634\u0647.",
        "output": "\u05d5\u05d4\u05d9\u05d0 \u05e2\u05db\u05e9\u05d9\u05d5 \u05d1\u05e9\u05e0\u05d5\u05ea \u05d4\u05e9\u05de\u05d5\u05e0\u05d9\u05dd \u05dc\u05d7\u05d9\u05d9\u05d4.",
        "category": "Translation 392.json"
    },
    {
        "instruction": "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.",
        "input": "turn right and turn left",
        "output": "I_TURN_RIGHT I_TURN_LEFT",
        "category": "Text to Code 393.json"
    },
    {
        "instruction": "You are given a sentence in Persian. Your job is to translate the Farsi sentence into Galician.",
        "input": "\u0686\u0648\u0646 \u062f\u0631 \u0647\u0646\u062f \u0645\u0627 \u0628\u0627\u0644\u0627\u0628\u0631\u0647\u0627\u06cc \u0628\u0631\u0642\u06cc \u067e\u0631 \u0632\u0631\u0642 \u0648 \u0628\u0631\u0642 \u0646\u062f\u0627\u0631\u06cc\u0645 \u062a\u0627 \u0645\u0627 \u0631\u0627 \u0627\u0632 \u067e\u0644\u0647 \u0647\u0627 \u0628\u0627\u0644\u0627 \u0628\u0628\u0631\u062f \u0645\u062b\u0644 \u06a9\u0634\u0648\u0631\u0647\u0627\u06cc \u062a\u0648\u0633\u0639\u0647 \u06cc\u0627\u0641\u062a\u0647.",
        "output": "Posto que na India non temos cadeiras elevadoras para subir coma nos pa\u00edses desenvolvidos,",
        "category": "Translation 394.json"
    },
    {
        "instruction": "You are given a sentence in Persian. Your job is to translate the Farsi sentence into Italian.",
        "input": "\u0648 \u0622\u0646 \u0646\u0642\u0634\u0647 \u0627\u064a \u0631\u0627 \u0628\u0627\u0632 \u0645\u064a \u06a9\u0646\u062f.",
        "output": "E si apre una mappa.",
        "category": "Translation 395.json"
    },
    {
        "instruction": "You are given a sentence in Persian. Your job is to translate the Farsi sentence into Polish.",
        "input": "\u0648 \u0622\u0646\u0686\u0647 \u06a9\u0647 \u0622\u0646\u0647\u0627 \u0645\u062a\u0648\u062c\u0647 \u0634\u062f\u0646\u062f \u0627\u06cc\u0646 \u0627\u0633\u062a \u06a9\u0647 \u062c\u0646\u06af \u0628\u0627 \u0645\u0648\u0627\u062f \u0645\u062e\u062f\u0631",
        "output": "Ale w ko\u0144cu zrozumieli, \u017ce wojna z narkotykami wcale nie chroni ich dzieci.",
        "category": "Translation 396.json"
    },
    {
        "instruction": "You are given a sentence in Persian. Your job is to translate the Farsi sentence into Portugese.",
        "input": "\u0628\u0627 \u062e\u0648\u062f\u0645 \u0645\u06cc\u06af\u0645 \u060c \u0627\u0645\u0631\u0648\u0632 \u0686\u06cc \u067e\u06cc\u062f\u0627 \u0645\u06cc \u06a9\u0646\u06cc \u061f",
        "output": "Quer dizer, o que vou encontrar hoje?",
        "category": "Translation 397.json"
    },
    {
        "instruction": "You are given a sentence in Portuguese. Your job is to translate the Portuguese sentence into English.",
        "input": "Porque raz\u00e3o ela \u00e9 mais picada do que eu?",
        "output": "Why does she receive more bites than I do?",
        "category": "Translation 398.json"
    },
    {
        "instruction": "You are given a sentence in Portuguese. Your job is to translate the Portuguese sentence into Japanese.",
        "input": "Vou regressar ao dia de hoje, agora, e quero mostrar-vos onde est\u00e1 o Voyager 1.",
        "output": "\u4eca\u65e5\u306e\u65e5\u4ed8\u4eca\u73fe\u5728\u306b\u623b\u3063\u3066\u30dc\u30a4\u30b8\u30e3\u30fc\uff11\u53f7\u304c\u3069\u3053\u306b\u3044\u308b\u304b\u304a\u898b\u305b\u3057\u307e\u3059",
        "category": "Translation 399.json"
    },
    {
        "instruction": "Write a correct answer to the given question based on its associated fact. Make sure that your answer is contained in the associated fact. Don't be creative and introduce any new word that is not mentioned in the associated fact! Remember that the associated fact has been rearranged to form the question. So, the correct answer words must lie within the associated fact. The correct answer can be a word, phrase, or even a sentence.",
        "input": "Fact: The hand can be used to detect texture. \nQuestion: What is used to detect texture?",
        "output": "hand.",
        "category": "Question Answering 40.json"
    },
    {
        "instruction": "You are given a sentence in Portuguese. Your job is to translate the Portuguese sentence into Spanish.",
        "input": "Mas isso contribui para que as pessoas n\u00e3o queiram partilhar os seus rabiscos.",
        "output": "Pero esto, en efecto, contribuye a que la gente no quiera ni mostrar sus garabatos.",
        "category": "Translation 400.json"
    },
    {
        "instruction": "You are given a sentence in Portuguese. Your job is to translate the Portuguese sentence into Arabic.",
        "input": "Portanto, mantenham o mist\u00e9rio da energia negra em mente porque eu agora vou-vos contar tr\u00eas pontos-chave sobre a teoria das cordas.",
        "output": "\u0623\u0630\u0646 \u0645\u0639 \u0627\u0644\u0627\u062d\u062a\u0641\u0627\u0638 \u0628\u063a\u0645\u0648\u0636 \u0627\u0644\u0637\u0627\u0642\u0629 \u0627\u0644\u0645\u0628\u0647\u0645\u0629 \u0641\u064a \u062e\u0644\u0641\u064a\u0629 \u0639\u0642\u0644\u0643\u0645 \u062d\u064a\u062b \u0633\u0623\u0642\u0648\u0645 \u0628\u0625\u062e\u0628\u0627\u0631\u0643\u0645 \u0628 \u062b\u0644\u0627\u062b\u0629 \u0623\u0634\u064a\u0627\u0621 \u0631\u0626\u064a\u0633\u064a\u0629 \u0639\u0646 \u0646\u0638\u0631\u064a\u0629 \u0627\u0644\u0623\u0648\u062a\u0627\u0631",
        "category": "Translation 401.json"
    },
    {
        "instruction": "You are given a sentence in Portuguese. Your job is to translate the Portuguese sentence into Hebrew.",
        "input": "E esta fal\u00e1cia prov\u00e9m da idealiza\u00e7\u00e3o de um passado do qual j\u00e1 nos esquecemos.",
        "output": "\u05d5\u05d4\u05d0\u05e9\u05dc\u05d9\u05d4 \u05e0\u05d5\u05d1\u05e2\u05ea \u05de\u05e2\u05e9\u05d9\u05d9\u05ea \u05d0\u05d9\u05d3\u05d9\u05d0\u05dc\u05d9\u05d6\u05e6\u05d9\u05d4 \u05dc\u05e2\u05d1\u05e8 \u05e9\u05d0\u05d5\u05ea\u05d5 \u05e9\u05db\u05d7\u05e0\u05d5.",
        "category": "Translation 402.json"
    },
    {
        "instruction": "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.",
        "input": "I_TURN_RIGHT I_TURN_RIGHT I_WALK I_TURN_RIGHT I_TURN_RIGHT I_WALK I_TURN_LEFT I_TURN_LEFT I_RUN",
        "output": "run opposite left after walk opposite right twice, walk opposite right twice and run opposite left",
        "category": "Code to Text 404.json"
    },
    {
        "instruction": "You are given a sentence in Portuguese. Your job is to translate the Portuguese sentence into Italian.",
        "input": "Quantas vidas isso afetou?",
        "output": "Su quante persone ha inciso quella decisione?",
        "category": "Translation 405.json"
    },
    {
        "instruction": "You are given a sentence in Portuguese. Your job is to translate the Portuguese sentence into Polish.",
        "input": "Pedi um raio-X. Quando o resultado apareceu normal, o meu colega que estava a reavaliar o doente verificou alguma dor no quadrante inferior direito e chamou os cirurgi\u00f5es.",
        "output": "Zarz\u0105dzi\u0142em rentgen nerki. Okaza\u0142a si\u0119 zdrowa. M\u00f3j kolega dokonuj\u0105c ponownej diagnozy zauwa\u017cy\u0142 wra\u017cliwo\u015b\u0107 w prawej dolnej \u0107wiartce brzusznej i wezwa\u0142 chirurg\u00f3w.",
        "category": "Translation 406.json"
    },
    {
        "instruction": "You are given a sentence in Portuguese. Your job is to translate the Portuguese sentence into Farsi.",
        "input": "Talvez n\u00e3o seja muito prov\u00e1vel, mas independentemente do que ele fizer, ele poder\u00e1 fazer uso destas compet\u00eancias de concep\u00e7\u00e3o que adquiriu.",
        "output": "\u0627\u062d\u062a\u0645\u0627\u0644\u0634 \u062e\u06cc\u0644\u06cc \u06a9\u0645 \u0627\u0633\u062a \u060c \u0648\u0644\u06cc \u062c\u062f\u0627 \u0627\u0632 \u0627\u06cc\u0646\u06a9\u0647 \u0686\u06a9\u0627\u0631\u0647 \u0645\u06cc \u200c \u0634\u0648\u062f \u060c \u0627\u0648 \u0642\u0627\u062f\u0631 \u0627\u0633\u062a \u0627\u0632 \u0647\u0645\u0647 \u200c \u06cc \u0645\u0647\u0627\u0631\u062a \u200c \u0647\u0627\u06cc \u0637\u0631\u0627\u062d\u06cc \u06a9\u0647 \u0641\u0631\u0627 \u06af\u0631\u0641\u062a\u0647 \u0627\u0633\u062a \u0628\u0647\u0631\u0647 \u0628\u0628\u0631\u062f.",
        "category": "Translation 407.json"
    },
    {
        "instruction": "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.",
        "input": "System Reference: may i ask near where?\nOriginal Reference: where do you want to be near to?.",
        "output": "0",
        "category": "Text Quality Evaluation 408.json"
    },
    {
        "instruction": "Write an incorrect answer to the given question based on the associated fact. You are also provided with the correct answer to the given question. Make sure that your incorrect answer is relevant and similar to the associated fact. Also, try to make the incorrect answer similar to the correct answer so that distinguishing the correct answer from the incorrect answer is not very easy. Make sure you don't accidentally provide another correct answer! Also, make sure they sound reasonable (e.g., might be on a school pop quiz). A good incorrect answer can be constructed using words associated with the question, but not the correct answer. For example, for the question \"What helps plants survive?\", using words like \"weeds\", \"vase\", \"bee\" (associated with \"plant\"), or \"first aid\", \"parachute\", \"accident\" (associated with \"survive\") etc. Your incorrect answers make the question hard, so these results in good incorrect answers.",
        "input": "Fact: Placental mammals get oxygen from the air. \nQuestion: Where do placental mammals get oxygen from? \nCorrect Answer: air.",
        "output": "bubbles., mud., water.",
        "category": "Wrong Candidate Generation 41.json"
    },
    {
        "instruction": "The input contains a debate topic, an argument on the topic and a keypoint, separated by \"<sep>\". Your task is to answer if the keypoint matches the argument and summarizes exactly what the argument means, in the context of the given topic.",
        "input": "Topic: We should adopt libertarianism<sep>Argument: Libertarianism is the most free way for people to live.<sep>Keypoint: Libertarianism increases happiness/fulfilment",
        "output": "False",
        "category": "Text Matching 410.json"
    },
    {
        "instruction": "In this task, you are given a multiple-choice question and you have to pick the correct option. Answer with option indexes (i.e., \"A\", \"B\", \"C\", and \"D\").",
        "input": "A creature lives in a portion of forested area, and only is able to live in that area. A group of bipeds begin to make their own homes in that space. The creature which originally lived there is most likely to (A) share their space (B) sell that space (C) lose their space (D) fight for space",
        "output": "C",
        "category": "Question Answering 411.json"
    },
    {
        "instruction": "Here are two questions (Question1 and Question2). If these questions have the same meaning and same answer, answer \"Yes\", otherwise \"No\".",
        "input": "Question1: What is your favorite song of 2016?, Question2: What was your favorite song of 2016?",
        "output": "Yes",
        "category": "Text Matching 412.json"
    },
    {
        "instruction": "You are given two sentences(Sentence1 and Sentence2). Answer \"Yes\" if these sentences are a paraphrase of one another, otherwise answer \"No\".",
        "input": "Sentence1: Microsoft said Friday that it is halting development of future Macintosh versions of its Internet Explorer browser , citing competition from Apple Computer 's Safari browser ., Sentence2: Microsoft will stop developing versions of its Internet Explorer browser software for Macintosh computers , saying that Apple 's Safari is now all that Apple needs .",
        "output": "Yes",
        "category": "Text Matching 413.json"
    },
    {
        "instruction": "You are given a question. You need to detect which category better describes the question. A question belongs to the description category if it asks about description and abstract concepts. Entity questions are about entities such as animals, colors, sports, etc. Abbreviation questions ask about abbreviations and expressions abbreviated. Questions regarding human beings, description of a person, and a group or organization of persons are categorized as Human. Quantity questions are asking about numeric values and Location questions ask about locations, cities, and countries. Answer with \"Description\", \"Entity\", \"Abbreviation\", \"Person\", \"Quantity\", and \"Location\".",
        "input": "How many endangered species are there in the world ?",
        "output": "Quantity",
        "category": "Question Understanding 414.json"
    },
    {
        "instruction": "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.",
        "input": "jump left and turn right twice",
        "output": "I_TURN_LEFT I_JUMP I_TURN_RIGHT I_TURN_RIGHT",
        "category": "Text to Code 415.json"
    },
    {
        "instruction": "You are given a review about a place. You need to provide a rating from \"1 star\" to \"5 stars\" for this place.",
        "input": "We were eating here so we could easily get into the club.  It turns out the food is actually pretty good.  They sat us just a few minutes late.  We found a nice spot by the bar to have a few pre dinner drinks.  The drinks are pricey but the setting is great.\\n\\nWe started with the chicken satay and pork rolls.  Both were excellent.  The peanut sauce with the satay was great.  For my meal I had the filet with noodles.  The sauce was great.  I would have liked a little more meat, but I was still very happy with my meal.\\n\\nFor desert we shared the giant fortune cookie.  One half was filled with dark chocolate mouse.  The other half was filled white chocolate mouse.\\n\\nOverall it was a very good meal.",
        "output": "4 stars",
        "category": "Sentiment Analysis 418.json"
    },
    {
        "instruction": "In this task, you are given a question. You have to answer the question based on your information.",
        "input": "Which host of Through the Wormhole also won Best Supporting Actor?",
        "output": "Morgan Freeman",
        "category": "Question Answering 419.json"
    },
    {
        "instruction": "In this task, you are given a question and a context passage. You have to answer the question based on the given passage.",
        "input": "What was Russia a part of?, Context: The post-Imperial nature of Russian subdivision of government changed towards a generally autonomous model which began with the establishment of the USSR (of which Russia was governed as part). It was liberalized in the aftermath of the Soviet Union, with the reforms under Boris Yeltsin preserving much of the Soviet structure while applying increasingly liberal reforms to the governance of the constituent republics and subjects (while also coming into conflict with Chechen secessionist rebels during the Chechen War). Some of the reforms under Yeltsin were scaled back by Vladimir Putin.",
        "output": "the USSR, Soviet Union",
        "category": "Question Answering 421.json"
    },
    {
        "instruction": "In this task, you are given two facts, and a multiple-choice question. Based on the given facts, answer the question with index of the correct option (e.g, \"A\").",
        "input": "Fact1: Air pollution harms the respiratory and circulatory systems., Fact2: Dust contributes to air pollution., Question: What harms the respiratory and circulatory systems? (A) oil (B) Cars (C) coal (D) water (E) air (F) sulfur (G) bees (H) dust",
        "output": "H",
        "category": "Question Answering 423.json"
    },
    {
        "instruction": "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.",
        "input": "I_TURN_LEFT I_TURN_LEFT I_TURN_LEFT I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN I_TURN_RIGHT I_RUN",
        "output": "turn left thrice and run around right twice, run around right twice after turn left thrice",
        "category": "Code to Text 424.json"
    },
    {
        "instruction": "In this task, you're given a review from Amazon and category of the product based on the review given by the user and your task is classify whether the given category match the review. Generate \"True\" if given review and its category match, otherwise generate \"False\".",
        "input": "Reviews: These are junk! Both bulbs have burned out within a two month period!! I cannot believe that this company can be in business with such poor quality. I have used infrared lights for my ball python for many years now and I get a varied range of months from a bulb, but I have never gone through two bulbs in a matter of two months! I am very disappointed. \n Category: pet_products",
        "output": "True",
        "category": "Text Categorization 425.json"
    },
    {
        "instruction": "In this task, you're given reviews from Amazon's food products and a summary of that review. Your task is to classify whether the given summary matches the original review. Generate \"True\" if the given review and its summary match, otherwise generate \"False\".",
        "input": "Reviews: Box for the product was crushed \u2026 and so was the product itself. Crushed box was inside a perfectly fine, undamaged Amazon mailing box with the other products that I ordered at the same time. I am returning and hopefully will receive one that is not crushed this time. \n Summary: Was mailed crushed inside a perfectly good amazon box",
        "output": "True",
        "category": "Summarization 426.json"
    },
    {
        "instruction": "In this task, you're given a review from Amazon. Your task is to generate a rating for the product on a scale of 1-5 based on the review. The rating means 1: extremely poor, 2: poor, 3: neutral, 4: good, 5: extremely good.",
        "input": "We have two Panasonic microwave ovens and the magnets in this cover will not stick to either. There is a slight attraction, but not anywhere near enough. So, I thought I'd stick it to the side of the refrigerator, which is next to one of the microwaves, where there are many magnetized do-dads holding just fine. The cover doesn't fall off, but immediately slides down the side to the floor. I don't know if the manufacturer got a bad batch of weak magnets or what the problem may be, but it is basically a complete loss to me. For $12 I won't bother sending it back. Shame for lack of quality control.",
        "output": "1",
        "category": "Sentiment Analysis 428.json"
    },
    {
        "instruction": "In this task, you're given a review from Amazon and rating for the product on a scale of 1-5 based on the review. The rating means 1: extremely poor, 2: poor, 3: neutral, 4: good, 5: extremely good. Your task is to generate whether the rating matches the review or not. Answer with \"True\" if the sentence belongs to that section, otherwise answer with \"False\"",
        "input": "Review: We absolutely love this French press, its easy to use, great quality and its a great size for two people. Works great for both hot and cold brew. Excellent product. \n Rating: 1",
        "output": "False",
        "category": "Sentiment Analysis 429.json"
    },
    {
        "instruction": "In this task, You are given a review of Amazon's food products. Your task is to divide them into two classes: negative or positive, depending on the content of the review.",
        "input": "Finally, a camisole that does not stick to the top shirt when layering. These feel silky and are just the right weight. The white is a little see through but not too thin. I can wear it modestly under a semi sheer white summer blouse. I would not wear these alone but they are great as an undergarment.",
        "output": "positive",
        "category": "Sentiment Analysis 430.json"
    },
    {
        "instruction": "Translate from Hindi to English such that it preserves the original meaning  Perform complete translation (partially translated sentences are considered incorrect).",
        "input": "\u092e\u0941\u091d \u092a\u0930 \u0932\u0947\u091f\u094b, \u091c\u0932\u094d\u0926\u0940!",
        "output": "Get on me, quick!",
        "category": "Translation 442.json"
    },
    {
        "instruction": "The task is about translation from Telugu to English. While performing the translation you must preserve the original meaning. Do not include any words which are only limited to your native place.",
        "input": "\u0c2e\u0c40\u0c30\u0c41\u0c28\u0c3e\u0c15\u0c41\u0c24\u0c46\u0c32\u0c41\u0c38\u0c3e",
        "output": "Do you understand me?",
        "category": "Translation 443.json"
    },
    {
        "instruction": "You will be given a context, a subject and a relation. Your task is to generate a question based on the subject and relation. The generated question should include the given subject. Try to use a minimum number of words that are not present in either context, subject or relation while generating question.",
        "input": "Context : He was born on January 2, 1869 in Brooklyn, New York to Philip Bayard Veiller. \nSubject : Bayard Veiller \nRelation : occupation",
        "output": "What kind of  occupation does Bayard Veiller have?",
        "category": "Question Generation 444.json"
    },
    {
        "instruction": "Generate a question which can yield the answer mentioned in the input. Generated question must be answered by the answer provided in input, without using any extra knowledge.",
        "input": "Context : ``The Unbearable Like-Likeness of Gene'' is the eighth episode of the third season of the animated comedy series Bob's Burgers. \nAnswer : Bob's Burgers",
        "output": "What is the series called that The Unbearable Like-Likeness of Gene belongs to?",
        "category": "Question Generation 445.json"
    },
    {
        "instruction": "Generate a correct and concise answer for the question based on the words in the context.",
        "input": "Context : Recollections of the Yellow House (Portuguese: Recorda\u00e7\u00f5es da Casa Amarela) is a 1989 Portuguese film directed by Jo\u00e3o C\u00e9sar Monteiro. \nQuestion : The director of Recollections of the Yellow House is who?",
        "output": "Jo\u00e3o C\u00e9sar Monteiro",
        "category": "Question Answering 446.json"
    },
    {
        "instruction": "Classify the relation of question with context to one of these categories: 1) award received, 2) based on, collection, 3) conflict, 4) constellation, 5) convicted of, 6) date of death, 7) director, 8) drafted by, 9) educated at, 10) medical condition, 11) military branch, 12) narrative location, 13) occupation, 14) original network, 15) parent company, 16) point in time, 17) production company, 18) residence, 19) series, 20) service entry, 21) sex or gender, 22) spouse, 23) standards body question.",
        "input": "Context : The Sivakasi riots of 1899 are a series of communal disturbances which occurred during 6 June 1899 in Sivakasi, Tamil Nadu, India. \nQuestion : What was the date of Sivakasi riots of 1899?",
        "output": "point in time",
        "category": "Question Understanding 447.json"
    },
    {
        "instruction": "Translate from English to Hindi.",
        "input": "I'm sorry to hear that.",
        "output": "\u0938\u0941\u0928\u0915\u0930 \u0905\u092b\u0938\u094b\u0938 \u0939\u0942\u0906.",
        "category": "Translation 448.json"
    },
    {
        "instruction": "Languages typically provide more than one grammatical construction to express certain types of messages. Your task is to generate a senetence with the same meaning as given sentence, but with different grammatical construction.",
        "input": "Mary chirped a woman her greeting",
        "output": "Mary chirped her greeting to a woman",
        "category": "Paraphrasing 449.json"
    },
    {
        "instruction": "Translation from English to Telugu.",
        "input": "I can't stand that tickling'.",
        "output": "\u0c15\u0c4d\u0c32\u0c3f\u0c28\u0c4d ': \u0c28\u0c47\u0c28\u0c41 \u0c08\u0c21\u0c4d\u0c2a\u0c41 \u0c05\u0c28\u0c41\u0c15\u0c42\u0c32\u0c3f\u0c02\u0c1a\u0c26\u0c41.",
        "category": "Translation 450.json"
    },
    {
        "instruction": "You will be given a context and a question in Spanish. Your job is to generate answers that are at least THREE words long.\n The answers need to be context specific and can not be general knowledge or a random guess.",
        "input": "CONTEXT: Historia \nRuman\u00eda creci\u00f3 notablemente tras la Primera Guerra Mundial. La derrota y desmembramiento del Imperio austroh\u00fangaro le permiti\u00f3 adquirir Bucovina, parte de Austria desde 1775, y Transilvania, parte del Banato y los distritos de Cri\u015fana y Maramure\u015f, durante siglos parte de la Corona de Hungr\u00eda. El hundimiento del Imperio ruso, la revoluci\u00f3n y la posterior guerra civil le dieron la oportunidad de ocupar y posteriormente anexionarse Besarabia, que pertenec\u00eda a Rusia desde 1812. Todos estos territorios contaban con una mayor\u00eda de cultura rumana, aunque tambi\u00e9n albergaban abundantes minor\u00edas. El pa\u00eds hab\u00eda obtenido adem\u00e1s el sur de Dobruja inmediatamente antes del estallido de la Guerra Mundial, tras la derrota b\u00falgara en la Segunda Guerra Balc\u00e1nica en 1913. Aunque lo hab\u00eda perdido durante la guerra, lo recuper\u00f3 tras la derrota de los Imperios Centrales. En esta provincia, a diferencia de las dem\u00e1s adquisiciones, la poblaci\u00f3n de cultura rumana se hallaba en minor\u00eda.\nQUESTION: \u00bfCu\u00e1ndo aument\u00f3 Ruman\u00eda sus territorios de un modo destacado?",
        "output": "tras la Primera Guerra Mundial",
        "category": "Question Answering 454.json"
    },
    {
        "instruction": "This task is in Spanish. Based on the given context, generate a question which can be answered by the given context. Generate a question that has more than 7 words. You can paraphrase the given context while forming the question.\n Suggestion: The question may involve starting question words like WHERE, WHEN, HOW, WHAT (in Spanish).",
        "input": "CONTEXT: Colhuacan o Culhuac\u00e1n ([ko\u02d0l\u02c8waka\u02d0n]) fue un antiguo se\u00f1or\u00edo que se encontraba en la punta occidental de la pen\u00ednsula de Iztapalapa, en el valle de M\u00e9xico. Las fuentes mexicas y texcocanas dicen que Colhuacan fue fundado por los toltecas, que la convirtieron en su primera capital; sin embargo, Chimalpahin y las investigaciones arqueol\u00f3gicas posteriores ponen de manifiesto que el asentamiento ya exist\u00eda antes de la llegada de los toltecas al valle de M\u00e9xico. Fue fundado al final del per\u00edodo Cl\u00e1sico de Mesoam\u00e9rica, como resultado de la dispersi\u00f3n demogr\u00e1fica que sufri\u00f3 Teotihuacan en la \u00e9poca de su declive. Sus habitantes eran portadores de la cultura de la gran metr\u00f3poli, y esa era una de las causas de su gran prestigio. La legitimaci\u00f3n de los tlatoanis de M\u00e9xico-Tenochtitlan se debi\u00f3 a su relaci\u00f3n con el linaje gobernante de Colhuacan.\nANSWER: los toltecas",
        "output": "\u00bfQui\u00e9n fund\u00f3 Colhuacan seg\u00fan las fuentes mexicas y texcocanas?",
        "category": "Question Generation 455.json"
    },
    {
        "instruction": "You will be given a sentence containing a pronoun/person name and an emotion. From these implicit parameters, the main goal is to find the gender of the person (male / female).",
        "input": "My daughter made me feel furious.",
        "output": "female",
        "category": "Gender Classification 456.json"
    },
    {
        "instruction": "The input is a sentence. The sentence includes an emotion. The goal of the task is to classify the emotion in the sentence to one of the classes: 'fear', 'joy', 'anger', 'sadness'. The emotion mainly depends on the adverb within the sentence.",
        "input": "Ellen told us all about the recent depressing events.",
        "output": "sadness",
        "category": "Sentiment Analysis 457.json"
    },
    {
        "instruction": "Given a text, write a compressed version of it in a single sentence.",
        "input": "4. \"If you are like me, you are far more likely to regret what you did not do than what you do do.\"",
        "output": "You are far more likely to regret what you did not do than what you do.",
        "category": "Sentence Compression 460.json"
    },
    {
        "instruction": "Given an Amazon customer review, write a title for the review. The preferred titles are under fifteen words.",
        "input": "I love this... Just been on an overseas trip and all I needed was my eye fi card... while we were travelling I turned my camera and ipad on together and it transferred all my photos over so i could delete and fill it up again... no issue at all... 2,000 photos taken and transferred... everyone that watched though it was magic...",
        "output": "Magic transfers!",
        "category": "Title Generation 462.json"
    },
    {
        "instruction": "Given an Amazon review, indicate whether it is a 'Positive Review' or 'Negative Review'.",
        "input": "perfect fit, it took me a little while to figure out exaxtly what to physical demensions were on my laptop,<br />the &#34;demensions&#34; are what you need when purchasing an adapter, NOT the model # of the Lap Top.<br />as in The outside of your existing plug is 5.5 mm / & the inner hole accepts a 2.5 mm pin (drill bit)<br />I used drill bits to calculate the size of my adapter  / & 1mm=0.039 inch / 1/16 inch = 0.062 thousanthsinch / 3/32 = about 0.095 thousanths<br />so, 2mm = about 0.089 thousanths inch, a little under 3/32 Inch drill bit",
        "output": "Positive Review",
        "category": "Sentiment Analysis 463.json"
    },
    {
        "instruction": "In this task you're given a question and you have to paraphrase the question to create the output question while retaining the meaning of the original question.",
        "input": "Why do the former colonies of Britain tend to be wealthier overall than the former colonies of France, the Netherlands, Spain, or Portugal?",
        "output": "Why are former British colonies doing so well compared to Spanish/Portuguese/French colonies (there are exceptions, but the general trend is obvious)?",
        "category": "Question Rewriting 465.json"
    },
    {
        "instruction": "You will be given a sentence. Check whether the sentence is grammatically correct and is meaningful. If the sentence is grammatically correct, then answer with '1', otherwise answer with '0'.",
        "input": "John suddenly put the customers off.",
        "output": "1",
        "category": "Grammar Error Detection 466.json"
    },
    {
        "instruction": "In this task, you need to generate an appropriate title for the given summary of some paragraph. The generated title must be short and should include the main topic of the given text. Your summary should be less than 20 words long.",
        "input": "\"This is Philosophical Transactions from 1716, and Halley's paper - which is in Latin - is number five in the volume\".",
        "output": "The transit of science",
        "category": "Title Generation 477.json"
    },
    {
        "instruction": "Given a sentence, fill out the missing word with a 'no' or a number (between zero and ten). You should write the numbers with english alphabet, like: four instead of 4.",
        "input": "Scientists believe that giant squids live for less than ____ years.",
        "output": "five",
        "category": "Fill in The Blank 478.json"
    },
    {
        "instruction": "Given a sentence with a missing word, pick the answer option that best fills out the missing word in the sentence. Indicate each answer with its index ('a', 'b', 'c', 'd').",
        "input": "Most walkers do walk at least half an hour at a time, but fewer walk ____ or more times a week.\\Question: Choose the right answer from options given a) no b) two c) zero d) four",
        "output": "d",
        "category": "Fill in The Blank 480.json"
    },
    {
        "instruction": "The provided text is in English, and we ask you to translate the text to the Croatian language. Please bear in mind the following guidelines while translating: 1) We want a natural translation, a formal form. 2) Use the symbols like '#@%$-+_=^&!*' as-is. *Include* the special characters as suited when translating to Croatian. 3) Quantities like millions or billions should be translated to their equivalent in Croatian language 4) Note the input is all case-sensitive except for special placeholders and output is expected to be case-sensitive. 5) The output must have Croatian characters like \u017d or \u010d and the output must preserve the Croatian language characters. 6) The input contains punctuations and output is expected to have relevant punctuations for grammatical accuracy.",
        "input": "The next thing is that if you want to predict the effect of one species on another, if you focus only on that link, and then you black box the rest, it's actually less predictable than if you step back, consider the entire system -- all the species, all the links -- and from that place, hone in on the sphere of influence that matters most.",
        "output": "Idu\u0107a stvar jest, ako \u017eelite predvidjeti u\u010dinak jedne vrste na drugu, ukoliko se fokusirate samo na tu vezu, i ostavite sve ostalo da pro\u0111e kroz crnu kutiju, zapravo je manje predvidivo nego kad bi napravili korak unatrag, uzeli u obzir cijeli sustav -- sve vrste, sve veze -- i iz tog mjesta, fokusirali se na sferu utjecaja koja ima najvi\u0161e zna\u010di.",
        "category": "Translation 483.json"
    },
    {
        "instruction": "You are given a sentence and a question in the input. If the information provided in the sentence is enough to answer the question, label \"Yes\", otherwise label \"No\". Do not use any facts other than those provided in the sentence while labeling \"Yes\" or \"No\". There are only two types of valid responses: Yes and No.",
        "input": "Sentence: So he let her see his power. \nQuestion: Why did Steve's sister bring him a coat?",
        "output": "No.",
        "category": "Answerability Classification 49.json"
    },
    {
        "instruction": "Given a negotiation between two participants, answer 'Yes' if both participants agree to the deal, otherwise answer 'No'.",
        "input": "THEM: a ball and two books is what i need. nothing less.  YOU: okay, deal.",
        "output": "Yes",
        "category": "Dialogue State Tracking 503.json"
    },
    {
        "instruction": "In this task, you are given a context and four options. Each option is a suggested ending for the context. You should read the context and pick the best ending for the context. Please answer with \"A\", \"B\", \"C\", and \"D\". ",
        "input": "[header] How to make a fake fire [title] Cut your \" flames. [step] \" in this method, we use the airflow from a fan to cause a fake fabric \" flame \" to billow and blow. The size of your flame will depend on the desired size of your fake fire or the space limitations of your fireplace. <sep> (A) Use as much fabric as it can hold. [substeps] Cut your \" flames \" in fourths for a realistic, toddler-look. (B) Taking these measures into account, cut flames accordingly. [substeps] When it comes to cutting flames, you have several options. (C) The exact measurements you may need will depend on the space requirements of your fireplace. [substeps] Approximately 3 inches from the edge of your fireplace mantel is the approximate size of your flame. (D) You will need a long piece of string or 2 m lengths and a block of cardboard. You will also need a small piece of wire that is slightly longer than the actual flame, or maybe more.",
        "output": "B",
        "category": "Text Completion 508.json"
    },
    {
        "instruction": "In this task, you are given a question containing a blank (_) and two options. You should pick the best option to answer the question. Please answer with \"A\" or \"B\".",
        "input": "Angela pruned the roses but Lindsey refused so _ ended up with cuts on her hands. (A) Angela (B) Lindsey",
        "output": "A",
        "category": "Coreference Resolution 511.json"
    },
    {
        "instruction": "This task is about classifying the similarity of two sentences. The sentences can be classified as (a) SIMILAR - similar to each other, and (b) DISSIMILAR - not similar to each other. Sentences that have the same RDF relationship in terms of [subject, predicate, object] are similar to each other. The input is a list of two sentences and the output is either SIMILAR or DISSIMILAR.",
        "input": "['Ixayra medina rosa is from the province of baoruco', 'The Rice Boat serves Chinese food, price range is cheap, customer service average,  in City Centre,  family friendly,  located near Express by Holiday Inn']",
        "output": "DISSIMILAR",
        "category": "Text Matching 529.json"
    },
    {
        "instruction": "In this task, you are given triplets. Each triplet is in the form of [subject, predicate, object]. Your task is to generate proper sentence that utilizes these triples. The objective is to construct a sentence that (a) captures the facts specified in the triples and (b) is a well-formed sentence easily understandable by a human. All triple values need not be used directly in the sentence as long as the facts are adequately captured.",
        "input": "[['Alimentum', 'food', 'Japanese'], ['Alimentum', 'priceRange', '\u00a320-25'], ['Alimentum', 'customer rating', 'high'], ['Alimentum', 'area', 'riverside'], ['Alimentum', 'near', 'Yippee Noodle Bar']]",
        "output": "Alimentum is situated near Yippee Noodle Bar in the riverside area, with a high customer rating it offers Japanese food in the price range of \u00a320-25., Near Yippee Noodle Bar in riverside is  Alimentum  serving Japanese food with a high customer rating and prices between \u00a320-25.",
        "category": "Data to Text 530.json"
    },
    {
        "instruction": "This task is about using the specified sentence and converting the sentence to Resource Description Framework (RDF) triplets of the form (subject, predicate object). The RDF triplets generated must be such that the triplets accurately capture the structure and semantics of the input sentence. The input is a sentence and the output is a list of triplets of the form [subject, predicate, object] that capture the relationships present in the sentence. When a sentence has more than 1 RDF triplet possible, the output must contain all of them.",
        "input": "Browns Cambridge is an inexpensive average restaurant.",
        "output": "[['Browns Cambridge', 'eatType', 'restaurant'], ['Browns Cambridge', 'priceRange', 'less than \u00a320']]",
        "category": "Information Extraction 532.json"
    },
    {
        "instruction": "A question is presented to you in this task, and your job is to write a potentially correct answer.",
        "input": "what year michael jordan came in the nba?",
        "output": "1984 NBA Draft",
        "category": "Question Answering 534.json"
    },
    {
        "instruction": "In this task, you need to answer the given multiple-choice question on the gain. Gain is the value by which to multiply the input. Classify your answers into 'a', 'b', 'c', 'd', and 'e'.",
        "input": "Problem: a student needs 60 % of the marks on a test to pass the test . if the student gets 80 marks and fails the test by 40 marks , find the maximum marks set for the test . \nOptions: a ) 180 , b ) 200 , c ) 220 , d ) 240 , e ) 260",
        "output": "b",
        "category": "Question Answering 540.json"
    },
    {
        "instruction": "Given a category and a set of five words, find the word from the set that does not belong (i.e. is the least relevant) with the other words in the category. Words are separated by commas.",
        "input": "Category: mode of transportation \nWords: fly, swim, waggle, soar, wave",
        "output": "waggle",
        "category": "Word Semantics 541.json"
    },
    {
        "instruction": "In this task, you need to answer the given multiple-choice question on the general math. Classify your answers into 'a', 'b', 'c', 'd', and 'e'.",
        "input": "Problem: find the value of ( 100 + 20 / 90 ) \u00d7 90 \nOptions: a ) 4520 , b ) 9100 , c ) 9150 , d ) 8120 , e ) 9020",
        "output": "e",
        "category": "Question Answering 542.json"
    },
    {
        "instruction": "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'.",
        "input": "Problem: in an intercollegiate competition that lasted for 3 days , 185 students took part on day 1 , 150 on day 2 and 200 on day 3 . if 100 took part on day 1 and day 2 and 110 took part on day 2 and day 3 and 50 took part on all three days , how many students took part only on day 3 ? \nOptions: a ) 45 , b ) 35 , c ) 55 , d ) 30 , e ) 40",
        "output": "e",
        "category": "Question Answering 544.json"
    },
    {
        "instruction": "Given a set of five words, generate the word from the set that does not belong (i.e. is the least relevant) with the other words. Words are separated by commas.",
        "input": "luke, warm, tangle, ok, fair",
        "output": "ok",
        "category": "Word Semantics 552.json"
    },
    {
        "instruction": "In this task, you are given a sentence in the Romanian language. Your job is to translate the Romanian sentence into the English language.",
        "input": "Cu toate acestea, nu exist\u0103 nicio poz\u0103 cu Peter Hollingworth din iunie dup\u0103 examin\u0103rile lui Herald de ieri.",
        "output": "There is, however, no photo of Peter Hollingworth in the June issue examined by the Herald yesterday.",
        "category": "Translation 557.json"
    },
    {
        "instruction": "In this task, you are given a sentence in the English language. Your job is to translate the English sentence into the Romanian language.",
        "input": "FRIENDS of Robert De Niro yesterday rallied around him after he was diagnosed with prostate cancer.",
        "output": "Prietenii lui Robert De Niro s-au adunat \u00een jurul lui ieri dup\u0103 ce a fost diagnosticat cu cancer la prostat\u0103.",
        "category": "Translation 558.json"
    },
    {
        "instruction": "Given a set of four words, generate the category that the words belong to. Words are separated by commas. The possible categories are social gathering, accomodation, physical property, measurement unit, corporate, nutritional value, boats, police punishment, location (proximity), card games, outdoor sport activity, military rank, baby animals, weather, consumer product, animals, boxing terminology, food, chocolate food, bird, type of sandwich, date status, body part, ocean, employment activity, moral characteristic, elements, poker, computers, construction, guitar part, shady activities, physical activity, kitchenware, temperature, type of rigidity, emotional status, season, mode of transportation, window material, activity, emotional display, geographical property, fried food, store status, widespread, aesthetic characteristic, alcoholic drinks, secretary duty, direction, personal characteristic, and animal.",
        "input": "nearer, close, right there, beside",
        "output": "location (proximity)",
        "category": "Text Categorization 562.json"
    },
    {
        "instruction": "In this task you will be given a string that only contains single digit numbers spelled out. The input string will not contain spaces between the different numbers. Your task is to return the number that the string spells out. The string will spell out each digit of the number for example '1726' will be 'oneseventwosix' instead of 'one thousand seven hundred six'.",
        "input": "sixeightseveneighttwoeightone",
        "output": "6878281",
        "category": "Program Execution 566.json"
    },
    {
        "instruction": "In this task you will be given a list of integers. A list contains numbers separated by a comma. You need to round every integer to the closest power of 2. A power of 2 is a number in the form '2^n', it is a number that is the result of multiplying by 2 n times. The following are all powers of 2, '2, 4, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096'. If an integer is exactly in equally far from two different powers of 2 then you should output the larger power of 2. The output should be a list of integers that is the result of rounding each integer int the input list to the closest power of 2. The output should include a '[' to denote the start of the output list and ']' to denote the end of the output list.",
        "input": "[37, 2000, 3841, 4775, 17, 58, 3, 178, 1209, 4722, 1401, 18, 62, 3]",
        "output": "[32, 2048, 4096, 4096, 16, 64, 4, 128, 1024, 4096, 1024, 16, 64, 4]",
        "category": "Program Execution 567.json"
    },
    {
        "instruction": "In this task you will be given a list of integers. You should find the minimum absolute difference between 2 integers in the list. The absolute difference is the absolute value of one integer subtracted by another. The output should be a single integer which is the smallest possible absolute distance.",
        "input": "[-65, -33, -9]",
        "output": "24",
        "category": "Program Execution 568.json"
    },
    {
        "instruction": "In this task you will be given a list of integers. You should find the maximum absolute difference between 2 integers in the list. The absolute difference is the absolute value of one integer subtracted by another. The output should be a single integer which is the largest possible absolute distance.",
        "input": "[65, -71, -58, 4, 79]",
        "output": "150",
        "category": "Program Execution 569.json"
    },
    {
        "instruction": "In this task, you are given a hateful post in Bengali that expresses hate or encourages violence towards a person or a group based on the protected characteristics such as race, religion, sex, and sexual orientation. You are expected to classify the post into two classes: personal or non-personal depending on the topic.",
        "input": " \u098f\u0987 \u09b8\u09ac \u0995\u09a5\u09be \u09ac\u09b2\u09c7 \u09b0\u09c7\u09a8\u09cd\u09a1\u09bf\u09df\u09be \u09b0 \u0995\u09bf\u099b\u09c1 \u09ac\u09b2\u09a6 \u0986\u09ae\u09be\u09a6\u09c7\u09b0 \u09a6\u09c7\u09b6\u09c7 \u09aa\u09c1\u09b6 \u0995\u09b0\u09be\u09b0 \u09aa\u09be\u09df\u09a4\u09be\u09b0\u09be \u0995\u09b0\u099b\u09c7 ",
        "output": "non-personal",
        "category": "Text Categorization 592.json"
    },
    {
        "instruction": "You are given a background paragraph that describes one or more causal or qualitative relationships such as a relationship in economics or a scientific law and a story that makes use of the concepts or the relationship described in the provided paragraph. You are also given a question about the story that requires an understanding of the relationship described in the background paragraph and the story. You need to come up with an answer to the given question; the answer will be a span from either the question or the story. In order to correctly answer the given question, you need to understand the relationship mentioned in the background paragraph and should be able to use it to understand that in the story. Your answer can not consist of any word that is not mentioned in any of these: the background paragraph, the story, or the question. You can directly copy and paste a span from the story or the question while answering the given question.",
        "input": "Background Paragraph: Surface temperature differences in turn cause pressure differences. A hot surface warms the air above it causing it to expand and lower the density and the resulting surface air pressure. The resulting horizontal pressure gradient moves the air from higher to lower pressure regions, creating a wind, and the Earth's rotation then causes deflection of this air flow due to the Coriolis effect. The simple systems thus formed can then display emergent behaviour to produce more complex systems and thus other weather phenomena.  Large scale examples include the Hadley cell while a smaller scale example would be coastal breezes. \nStory: Mark was visiting southern Africa as an exchange student. He was amazed by the beauty of Namib Desert, which is located mostly in Namibia. He kind of enjoyed the hot surface of the desert. Next to Namib desert is the grasslands of  Botswana. He noticed that the surface temperature was much lower there. \nQuestion: Would the air density in Grasslands in Botswana be higher or lower than in Namib Desert?",
        "output": "higher.",
        "category": "Question Answering 60.json"
    },
    {
        "instruction": "The input is a tweet which can be classified as Hate Speech, Offensive or Normal. Given such a tweet, output the class the tweet belongs to. Hate Speech will contain threatening language towards the community targeted. Offensive language will contain abusive or discriminatory language towards the community targeted.",
        "input": "if you are a woman and you drive over <number> mph on the freeway you are a lesbian sorry i do not make the rules do not worry we will take care of you now",
        "output": "Normal",
        "category": "Toxic Language Detection 605.json"
    },
    {
        "instruction": "The input is a tweet which can be Hate Speech or Offensive. Given such a tweet, output a phrase from the tweet that makes it hate speech or offensive. The output should contain only one such phrase. The output has to be from within the tweet itself. Do not generate words or phrases not present in the tweet.",
        "input": "sandalphon not allowed to be in any hot attire that selfish bitch god",
        "output": "bitch",
        "category": "Toxic Language Detection 607.json"
    },
    {
        "instruction": "Given a statement about date and time, state whether the statement is true or false. The number of date/time operands in the statement ranges between 2 and 3. Let's say the values are denoted by t1, t2 and t3. The statements follow one of the following ten templates: 't1 occurs before t2, t1 doesn't occur before t2, t1 occurs after t2, t1 doesn't occur after t2, t1 occurs between t2 and t3, t1 doesn't occur between t2 and t3, t1 occured before t2 but after t3, t1 occured after t2 but before t3, t1 didn't occur before t2 but after t3, t1 didn't occur after t2 but before t3'. The output should be either 'True' or 'False'.",
        "input": "Oct 20, 2003 occured before Sep 21, 1993 but after 21 January 1987",
        "output": "False",
        "category": "Misc. 610.json"
    },
    {
        "instruction": "Given a phrase describing the relationship between two words, extract the words and the lexical relationship between them. The relation has to be of the type 'MemberOf', 'MadeOf', 'Synonym', 'Entails', 'HasA', 'HasProperty', 'PartOf', 'Antonym' or 'IsA'. The output should have the format: word1 relation word2.",
        "input": "Act is a kind of art",
        "output": "act IsA art",
        "category": "Information Extraction 614.json"
    },
    {
        "instruction": "In this task, you are given inputs i and A, where i is an integer and A is a list. You need to output the first i elements of A, starting with the 1st element in A. i will always have a value less than the length of A",
        "input": "6, ['Z', '7199', '8551', 'x', '8559', 'o', '5105', '1039', '401', '2523', '4059', 'o']",
        "output": "Z, 7199, 8551, x, 8559, o",
        "category": "Program Execution 62.json"
    },
    {
        "instruction": "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: (1) when the individual's belief matches reality, (2) when the individual's belief does not match reality, (3) is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios.",
        "input": "Mia entered the basement. Hannah entered the basement. The asparagus is in the green_treasure_chest. Mia moved the asparagus to the blue_crate. Where is the asparagus really?",
        "output": "blue_crate",
        "category": "Question Answering 621.json"
    },
    {
        "instruction": "You are given two sentences. You have to find if there is entailment or agreement of the Hypothesis by the Premise. From the given pair of sentences, you should identify if there is enough information in the Premise to support the claim made in the Hypothesis. The Premise may not exactly be the same as Hypothesis. Your task is to return 'entails' if the premise supports hypothesis else return 'neutral'.",
        "input": "Premise: Moreover, Antarctic seas are uniquely subject to the impacts of ocean acidification, the result of oceans absorbing anthropogenic atmospheric carbon dioxide (CO2). \n Hypothesis: Ocean acidification occurs when excess carbon dioxide in the atmosphere causes the oceans to become acidic.",
        "output": "entails",
        "category": "Textual Entailment 623.json"
    },
    {
        "instruction": "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.",
        "input": "Hannah entered the bathroom. William entered the bathroom. The strawberry is in the blue_suitcase. William exited the bathroom. Hannah moved the strawberry to the green_bottle. Where was the strawberry at the beginning?",
        "output": "blue_suitcase",
        "category": "Question Answering 624.json"
    },
    {
        "instruction": "You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. Your task is to label each of the continuous conversations done by one speaker with the emotion detected in that particular part. Your labels can be one among the following: 'No emotion', 'surprise', 'happiness', 'sadness', 'anger', 'disgust'.",
        "input": " Person1:      Bob , did you see our supervisor ? I need him to sign this paper . \n Person2:  He is in his office , but you'd better choose your words carefully while talking to him . \n Person1:       What's up ? \n Person2:  Nothing . But he is in a bad mood today . \n Person1:       Thanks for the warning . \n Person2:  That's all right . ",
        "output": "No emotion,No emotion,No emotion,No emotion,happiness,happiness",
        "category": "Sentiment Analysis 627.json"
    },
    {
        "instruction": "You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. You are required to assign a label 'formal' if there is an absence of emotion and a presence of questions anywhere within the conversation. If such pattern is not found assign the label 'informal'.",
        "input": " Person1:       Guess what ?  \n Person2:What ? ",
        "output": "formal",
        "category": "Dialogue Act Recognition 628.json"
    },
    {
        "instruction": "You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. If the conversation begins with a question, label it '1' otherwise '0'.",
        "input": " Person1:     What would you like for your main course ?  \n Person2:  Steak , please .  \n Person1:      How would you like your steak ? Rare , medium-rare or well-done ?  \n Person2:  Well-done , please . ",
        "output": "1",
        "category": "Dialogue Act Recognition 629.json"
    },
    {
        "instruction": "In this task, you are given inputs i and A, where i is an integer and A is a list. You need to list all the elements of A after the first i elements. i will always have a value less than the length of A.",
        "input": "11, ['w', 'L', '9039', '5097', 'B', 'q', 'z', 'r', '4873', '4891', '6603', '3513', 'G', '8879', '4451', 'V', '4521', '419', 'V', '9055', '3075', '5501', '207', '5881']",
        "output": "3513, G, 8879, 4451, V, 4521, 419, V, 9055, 3075, 5501, 207, 5881",
        "category": "Program Execution 63.json"
    },
    {
        "instruction": "You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. Your task is to classify the conversation either convey 'No emotion' or 'Happiness' by providing '1' and '0', respectively.",
        "input": " Person1:      Honey , I \u2019 ll be right back !  \n Person2:  Where are you going ?  \n Person1:       I told you already ! I \u2019 m going to get my nails done .  \n Person2:  Again ? You just went last week ! You spend more time at the nail salon than you do here at home ! Honestly , why do you need a manicure every week ?  \n Person1:       Well , first of all , I like to pamper myself , and my nails look great . You should come with me !  \n Person2:  Why ? I don \u2019 t want to have nail polish or anything like that !  \n Person1:       They don \u2019 t only paint my nails ! The manicurist will remove my cuticles , file my nails , and apply at least nails coats of nail polish !  \n Person2:  Yeah , sounds like something I should definitely do . ",
        "output": "0",
        "category": "Sentiment Analysis 631.json"
    },
    {
        "instruction": "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.",
        "input": "Mia entered the garage. Charlotte entered the garage. The pineapple is in the blue_cupboard. Charlotte exited the garage. Mia moved the pineapple to the green_cupboard. Mia exited the garage. Charlotte entered the garage. Ethan entered the hallway. Ella entered the hallway. The carrot is in the red_cupboard. Ella exited the hallway. Ethan moved the carrot to the blue_crate. Ethan exited the hallway. Ella entered the hallway. Ethan entered the garage. Mia entered the garage. The cucumber is in the green_cupboard. Mia exited the garage. Ethan moved the cucumber to the blue_cupboard. Ethan exited the garage. Mia entered the garage. Ethan entered the bathroom. Ella entered the bathroom. The asparagus is in the green_pantry. Ella exited the bathroom. Ethan moved the asparagus to the green_bucket. Ethan exited the bathroom. Ella entered the bathroom. Where does Ethan think that Ella searches for the asparagus?",
        "output": "green_pantry",
        "category": "Question Answering 635.json"
    },
    {
        "instruction": "In this task, you're given a short article. Your job is to classify the article based on its category. Use the following classification labels, 0. World, 1. Sports, 2. Business, 3. Science or Technical. Label the text \"0\" if it contains information related to world. Label the text \"1\" if it contains information related to sports. Label the text \"2\" if it contains information related business. Label the text \"3\" if it contains science or technical related information. ",
        "input": "Well, it worked for Bill So let me get this straight: Barry Bonds used steroids, but he didn #39;t inhale?***Mr. Schwarzenegger, meet your new lieutenant governor.",
        "output": "1",
        "category": "Text Categorization 637.json"
    },
    {
        "instruction": "In this task, you are given an input i,A where i is an integer and A is an array. You need to find every ith element of A starting with the 1st element.",
        "input": "3, ['y', 'i', 'H', 'h', 'j', '2635', 'C', '679', '6221', 'F', 'M', '2145', 'Y', '7719', '7021', '6535', '1913', '6667', 'y', 'B', '8909', '7047', 'f', 'e', 'a', 'C', '2619', 'L', 'h', 'a', 'w', '5339', 'O', '7411', 'm', 's', '4625', 'Y', '4781', '9361']",
        "output": "y, h, C, F, Y, 6535, y, 7047, a, L, w, 7411, 4625, 9361",
        "category": "Program Execution 638.json"
    },
    {
        "instruction": "In this task, you will be presented with a question in Dutch language, and you have to write the part-of-speech tag for each word and punctuation in the question. Here is the list of part-of-speech tags used in this task: Adj: Adjective, Adv: Adverb, Art: Article, Conj: Conjunction, Int: Interjection, N: Noun, V: Verb, Num: Number, Misc: Miscellaneous, Pron: Pronoun, Prep: Preposition, Punc: Punctuation.",
        "input": "In een hoek van het opgravingsterrein gaapt een rond gat waarin alle sporen uit de Middeleeuwen verdwenen zijn .",
        "output": "Prep Art N Prep Art N V Art Adj N Adv Pron N Prep Art N V V Punc",
        "category": "Pos Tagging 639.json"
    },
    {
        "instruction": "In this task, you are given a short story consisting of exactly 5 sentences where the second sentence is missing. You are given two options and you need to select the one that best connects the first sentence with the rest of the story. Indicate your answer by 'Option 1' if the first option is correct, otherwise 'Option 2'. The incorrect option will change the subsequent storyline, so that at least one of the three subsequent sentences is no longer consistent with the story.",
        "input": "Sentence 1: Alex drove to the store to buy a beer. \n Sentence 3: A cop pulled him over immediately \n Sentence 4:  Alex spit out the beer in the cop's face \n Sentence 5:  He then drove off and the cop gave chase \n Option 1: He opened the beer while driving. \n Option 2: He opened the beer at home.",
        "output": "Option 1",
        "category": "Coherence Classification 64.json"
    },
    {
        "instruction": "In this task, you will be presented with a question in Dutch language, and you have to write the named entities from the question if present. B denotes the first item of a phrase and an I any non-initial word. Here is the list of terms used: person names (PER), organizations (ORG), locations (LOC) and miscellaneous names (MISC). There can be instances with no named entities, then return 'None'.",
        "input": "Dit heeft Horst K\u00c3\u0192\u00c6\u2019\u00c3\u201a\u00c2\u00b6hler , de in mei aangetreden topman van het IMF , gisteren gezegd in Bangkok , vanwaaruit hij een rondreis door Azi\u00c3\u0192\u00c6\u2019\u00c3\u201a\u00c2\u00ab maakt .",
        "output": "Horst: B-PER, K\u00c3\u0192\u00c6\u2019\u00c3\u201a\u00c2\u00b6hler: I-PER, IMF: B-ORG, Bangkok: B-LOC, Azi\u00c3\u0192\u00c6\u2019\u00c3\u201a\u00c2\u00ab: B-LOC",
        "category": "Named Entity Recognition 640.json"
    },
    {
        "instruction": "In this task, you will be presented with a question in Dutch language, and you have to write the person names from the question if present. B denotes the first item of a phrase and an I any non-initial word. Phrase used for the person name - PER. There can be instances with no person name entity, then return 'None'.",
        "input": "De ontdekking van het gen kan voor diabetici en atleten een doorbraak betekenen .",
        "output": "None",
        "category": "Named Entity Recognition 641.json"
    },
    {
        "instruction": "In this task, you will be presented with a question in Dutch language, and you have to write the location names from the question if present. B denotes the first item of a phrase and an I any non-initial word. Identifier used for the location name - LOC. . There can be instances with no location name entity, then return 'None'.",
        "input": "TV 1 22.10",
        "output": "None",
        "category": "Named Entity Recognition 642.json"
    },
    {
        "instruction": "Given a story, answer the question about the story. The question is the last sentence in the input. These stories can be difficult due to their length and how each story has at least one of the three following scenarios: the first is when the individual's belief matches reality, the second is when the individual's belief does not match reality, and the third is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios. Note that there are distractor sentences in each story that are unrelated to the question and are designed to confuse the reader.",
        "input": "Jacob entered the kitchen. Sophia entered the kitchen. The broccoli is in the green_bucket. Jacob moved the broccoli to the red_pantry. Amelia entered the porch. Sophia entered the porch. The peach is in the red_suitcase. Amelia moved the peach to the green_cupboard. Amelia is in the porch. Avery entered the porch. The grapefruit is in the green_cupboard. Amelia moved the grapefruit to the red_suitcase. Amelia entered the basement. Jacob entered the basement. The corn is in the blue_cupboard. Amelia moved the corn to the green_crate. Where was the corn at the beginning?",
        "output": "blue_cupboard",
        "category": "Question Answering 645.json"
    },
    {
        "instruction": "In this task, you are given inputs k, i, and A, where k and i are integers and A is a list. You need to find every ith element of A starting from the kth element. The process stops when the position of the next ith element exceeds the length of the list.",
        "input": "3, 10, ['m', '6023', '2597', '1527', '5683', '6203', '3591', 'q', '2797', '6931', 'S', '7769', 'Y', 'v', '9045', 'D', 'e', '3297', '5555', 'X', '2931', '4023', '1201', 'B', '2931', '7887', '1511']",
        "output": "2597, Y, 1201",
        "category": "Program Execution 646.json"
    },
    {
        "instruction": "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.",
        "input": "Sentence 1: Reactive elements are able to combine more easily with other elements. Sentence 2: Other surfaces should be able to withstand the elements and be easily maintained.",
        "output": "neutral",
        "category": "Textual Entailment 649.json"
    },
    {
        "instruction": "In this task, you are given a short story consisting of exactly 5 sentences where the second sentence is missing. You are given a candidate for the second sentence and you need to identify if the given sentence connects the first sentence with the rest of the story. Indicate your answer by \"Yes\" if it connects, otherwise \"No\". Do not generate anything else apart from \"Yes\" or \"No\". The given sentence is incorrect if it changes the subsequent storyline, so that at least one of the three subsequent sentences form a consistent story.",
        "input": "Sentence 1: Jennifer was so hungry. \n Sentence 3: She decided to get a pizza \n Sentence 4:  Jennifer took the pizza home \n Sentence 5:  She enjoyed it with her family \n Given Sentence 2: She had been out running errands all day.",
        "output": "Yes",
        "category": "Coherence Classification 65.json"
    },
    {
        "instruction": "In this task, you need to count the number of nouns/verbs in the given sentence.",
        "input": "Sentence: 'A number of brown and blue cones of ice cream'. Count the number of verbs in this sentence.",
        "output": "0",
        "category": "Pos Tagging 655.json"
    },
    {
        "instruction": "In this task, you're given the beginning and the ending of a three-part story. Your job is to complete the short story by writing a middle sentence that seamlessly connects  the first and last sentence. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra information when creating the middle sentence, and use names (e.g. Jack, Barbara,...) instead of pronouns (e.g. he / she) wherever possible.",
        "input": "Beginning: I like passing notes in class. Ending: The people that write back to me often become good friends of mine.",
        "output": "I end up finding out a lot about them., I pass notes to everyone in class., I pass notes to people I don't know., I send notes to everyone., Some people never write notes back, and some do.",
        "category": "Story Composition 66.json"
    },
    {
        "instruction": "In this task, you're shown a three-part story, with a beginning, middle, and ending. Your job is to slightly modify the middle part, so that the whole story becomes unlikely, improbable, or inconsistent. Generated sentences must minimally alter the given middle, with at most 4 new words added/existing words removed. Your sentence should be grammatically and syntactically correct. Also stick to the context of the given story. For example, if the story talks about \"doctors\", you can talk about \"health\" or \"diagnosis\", but don't mention \"aliens\". Avoid introducing any extra/irrelevant information, and use names instead of pronouns (e.g. he / she) wherever possible. Avoid simply negating the original middle, for example:  \"She likes cakes.\" is changed to \"She doesn't like cakes.\"",
        "input": "Beginning: Caleb was driving home from work one day when a car hit him in back. Middle: Caleb's insurance company did not want to pay for it. Ending: It took four years before Caleb received any money in the case.",
        "output": "Caleb's insurance company did not want to wait to pay for it.",
        "category": "Story Composition 67.json"
    },
    {
        "instruction": "In this task, you need to count the number of vowels (letters 'a', 'e', 'i', 'o', 'u') / consonants (all letters other than vowels) in the given sentence.",
        "input": "Sentence: 'a close up of a plate of food'. Count the number of vowels in the given sentence.",
        "output": "11",
        "category": "Program Execution 675.json"
    },
    {
        "instruction": "In this task, you will be shown a short story with a beginning, two potential middles, and an ending. Your job is to choose the middle statement that makes the story coherent / plausible by writing \"1\" or \"2\" in the output. If both sentences are plausible, pick the one that makes most sense.",
        "input": "Beginning: Lu got into the business of selling chemical enhancements via spam. Middle 1: Lu found it was very lucrative. Middle 2: Lu found it was very boring. Ending: Using humans to solve the CAPTCHAs, he can send his spam again.",
        "output": "1",
        "category": "Coherence Classification 68.json"
    },
    {
        "instruction": "In this task, you will be shown a short story with a beginning, two potential middles, and an ending. Your job is to choose the middle statement that makes the story incoherent / implausible by indicating 1 or 2 in the output. If both sentences are plausible, pick the one that makes less sense.",
        "input": "Beginning: Jessica and her boyfriend went to the theater to watch a movie. Middle 1: The ending of the movie was silly and humorous. Middle 2: The ending of the movie was silly and incomplete. Ending: Neither left the theater completely satisfied.",
        "output": "1",
        "category": "Coherence Classification 69.json"
    },
    {
        "instruction": "The task is to generate text based of an event. For the given event, there will be a person who does the action in the event (usually PersonX). Your task is to write that persons emotional reaction to the event, i.e. how that person feels after doing the action.",
        "input": "PersonX gets PersonX's grade",
        "output": "nervous.",
        "category": "Misc. 692.json"
    },
    {
        "instruction": "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.",
        "input": "PersonX keeps PersonY back",
        "output": "to prevent something",
        "category": "Misc. 693.json"
    },
    {
        "instruction": "You will be given a sentence that describes a restaurant. You will also be given a few categories of information regarding that sentence. Your task is to fill each of the categories with the appropriate information from the sentenece.",
        "input": "Sentence: xname is a coffee shop in riverside. It is family friendly with high prices and low ratings. ; Categories: rating, eattype, familyFriendly",
        "output": "rating[low], eattype[coffee shop], familyFriendly[yes]",
        "category": "Information Extraction 694.json"
    },
    {
        "instruction": "The task is to write a full sentence or two using all of the information given. The sentence(s) will be a brief review of a restaurant. Use all of the information provided.",
        "input": "name[xname], cuisine[Italian], price[moderate], rating[3 out of 5], location[riverside], familyFriendly[yes]",
        "output": "xname is a family-friendly establishment where you can buy spaghetti.  Maybe you can even enjoy it with a nice glass of wine next to the river. With reasonable ratings and moderate prices, it's an ideal place to feed your children.",
        "category": "Data to Text 695.json"
    },
    {
        "instruction": "In this task, you are given an utterance, which is a part of a conversation between a user and an agent. Your job is to detect the speaker. The user usually commands the agent to schedule events, retrieve event information, and check the schedule. While the agent's response is an answer to the user's questions or follow-up questions on the user's command. Answer with \"User\" or \"Agent\".",
        "input": "Does Kirari in Los Angeles have takeout?",
        "output": "user",
        "category": "Speaker Identification 696.json"
    },
    {
        "instruction": "In this task, answer 'Yes' if the frequency of the given word in the two sentences is equal, else answer 'No'.",
        "input": "Sentence1: 'the crowd of people are preparing the bananas to sell', Sentence2: 'a feminine shirtless man holding a bottle of wine in the kitchen with the refrigerator open'. Is the frequency of the word 'of' in two sentences equal?",
        "output": "Yes",
        "category": "Program Execution 697.json"
    },
    {
        "instruction": "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.",
        "input": "concept: Mali  question:  what kind of government did the mali empire have?",
        "output": "['Republic']",
        "category": "Question Answering 699.json"
    },
    {
        "instruction": "In this task, you're given the beginning and the middle of a three-part story. Your job is to complete the short story by writing a probable ending. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra information when creating the ending, and use names instead of pronouns (e.g. he / she) wherever possible.",
        "input": "Beginning: Alex was lying in bed and noticed a bad smell. Middle: Alex quickly discovered the problem.",
        "output": "Turns out it was his shoes because he didn't wear socks.",
        "category": "Story Composition 70.json"
    },
    {
        "instruction": "In this task, you need to replace a letter in the sentence with another given letter.",
        "input": "Sentence: 'closeup of two teddy bears in red scarves and a brown teddy bear'. Replace the letter 'i' with 'y' in the sentence.",
        "output": "closeup of two teddy bears yn red scarves and a brown teddy bear",
        "category": "Program Execution 708.json"
    },
    {
        "instruction": "In this task, you're given the middle and ending of a three-part story. Your job is to complete the short story by writing a probable beginning of the story. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra information when creating the beginning, and use names (e.g. Jack, Barbara,...) instead of pronouns (e.g. he / she) wherever possible.",
        "input": "Middle: AJ's mom refused to buy him any candy. Ending: AJ then began to feel sad.",
        "output": "AJ and his mom were at the grocery store.",
        "category": "Story Composition 71.json"
    },
    {
        "instruction": "This task is to translate the English language Input to Telugu Language Output",
        "input": "H - \u0c37\u0c4b risers",
        "output": "T - \u0c17\u0c23\u0c2e\u0c41 kosoura",
        "category": "Translation 715.json"
    },
    {
        "instruction": "This task is to translate the Telugu Language Input to English Language Output",
        "input": "\u0c2e\u0c39\u0c40\u0c02\u0c26\u0c4d\u0c30\u0c3e \u0c35\u0c3e\u0c30\u0c3f \u0c30\u0c3f\u0c35\u0c30\u0c4d\u0c38\u0c2c\u0c41\u0c32\u0c4d \u0c28\u0c3e\u0c17\u0c32\u0c3f, \u0c12\u0c15 \u0c2c\u0c32\u0c2e\u0c46\u0c56\u0c28, \u0c27\u0c43\u0c22\u0c28\u0c3f\u0c30\u0c4d\u0c2e\u0c3e\u0c23\u0c02\u0c17\u0c32 \u0c2e\u0c30\u0c3f\u0c2f\u0c41 \u0c28\u0c21\u0c2a\u0c21\u0c3e\u0c28\u0c3f\u0c15\u0c3f \u0c38\u0c41\u0c33\u0c41\u0c35\u0c48\u0c28 \u0c2a\u0c30\u0c3f\u0c15\u0c30\u0c02.",
        "output": "Mahindra's reversible plough is a robust, sturdy and easy to operate implement.",
        "category": "Translation 716.json"
    },
    {
        "instruction": "This task is to identify the language of a sentence correctly by classifying if it is English or Telugu",
        "input": "e) Always sleep alone.",
        "output": "English",
        "category": "Language Identification 717.json"
    },
    {
        "instruction": "In this task, you are given a sentence in the English language from the various articles. Your task is to translate the given English sentence into the Yoruba language. Please bear in mind the following guidelines while doing the translation: 1) Generated output should have natural language and formal form. The output sentence should not be a colloquial form of the input sentence. The generated output should be in natural language which is how you would type your queries in a text-based virtual assistant. 2) The words between quotation marks *SHOULD NOT* be translated. The output should keep those values intact and include the quotation marks around them as well. 3) Numbers and fully capitalized words like SEPTEMBER, or 10 HOURS *SHOULD NOT* be translated. Keep them as they are in the translations. 4) Do not localize measurement units like miles to kilometers during your translation. 5) Note the input is in sentence case except for special placeholders. Do the same in your translations.",
        "input": "He is one of the greatest exports of Nigerian football.",
        "output": "B\u1eb9\u0301\u1eb9\u0300 s\u00ecni \u00d3 j\u1eb9\u0301 \u1ecd\u0300kan l\u00e1ra \u00e0w\u1ecdn agb\u00e1b\u1ecd\u0301\u1ecd\u0300l\u00f9 N\u00e0\u00ecj\u00ed\u00edr\u00ed\u00e0 t\u00ed \u00f3 ti \u1e63\u00e0\u1e63ey\u1ecdr\u00ed n\u00edn\u00fa er\u00e9 b\u1ecd\u0301\u1ecd\u0300l\u00f9 l\u00e1gb\u00e0\u00e1y\u00e9.",
        "category": "Translation 718.json"
    },
    {
        "instruction": "In this task, you need to count the number of words in a sentence that contain the given letter",
        "input": "Sentence: 'a women with a tennis racquet in one hand and a towel in the other'. How many words contain the letter 's' in the sentence.",
        "output": "1",
        "category": "Program Execution 719.json"
    },
    {
        "instruction": "The input contains texts obtained from news articles, ted talks, movie transcripts, radio transcripts, science and technology texts, and other short articles curated from the web and professional translators. Your task is to translate the given Yoruba sentence into the English language. Please bear in mind the following guidelines while doing the translation: 1) Generated output should be natural language and formal form of each sentence in your language. The output sentence should not be a colloquial form of the input sentence. The generated output should be in natural language 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) Numbers and fully capitalized words like SEPTEMBER, or 10 HOURS *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. 5) Note the input is in sentence case except for special placeholders. Please do the same in your translations.",
        "input": "Mo w\u00e0 p\u1eb9\u0300l\u00fa \u1eb9\u0300, John ni m\u00f2 \u0144 s\u1ecd",
        "output": "I was with him, I mean John",
        "category": "Translation 720.json"
    },
    {
        "instruction": "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.",
        "input": "B\u00f3 til\u1eb9\u0300 j\u1eb9\u0301 p\u00e9 Ar\u00e1k\u00f9nrin Christensen ti f\u1eb9\u0301r\u1eb9\u0300\u1eb9\u0301 lo \u1ecdd\u00fan m\u00e9j\u00ec l\u1eb9\u0301w\u1ecd\u0300n, \u00f3 gb\u1eb9\u0301k\u1eb9\u0300 l\u00e9 J\u00e8h\u00f3f\u00e0, \u00f3 s\u00ec \u0144 l\u00e1y\u1ecd\u0300.",
        "output": "Yoruba",
        "category": "Language Identification 721.json"
    },
    {
        "instruction": "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.",
        "input": "Kierkegaard criticised Hegel's idealist philosophy in several of his works, particularly his claim to a comprehensive system that could explain the whole of reality. Where Hegel argues that an ultimate understanding of the logical structure of the world is an understanding of the logical structure of God's mind, Kierkegaard asserting that for God reality can be a system but it cannot be so for any human individual because both reality and humans are incomplete and all philosophical systems imply completeness. A logical system is possible but an existential system is not. \"What is rational is actual; and what is actual is rational\". Hegel's absolute idealism blurs the distinction between existence and thought: our mortal nature places limits on our understanding of reality;",
        "output": "Who was a notable critic of Hegel?, For whom did Kierkegaard argue reality cannot be a system?, According to Kierkegaard, why can't reality be a system for human beings?, Even though Kierkegaard does not believe in the possibility of an existential system of reality, what sort of system can exist?",
        "category": "Question Generation 73.json"
    },
    {
        "instruction": "In this task, you need to count the number of words in a sentence that end with the given letter. Answer with numbers and not words.",
        "input": "Sentence: 'a man doing a trick on a skateboard on a bench'. How many words end with the letter 'n' in the sentence.",
        "output": "3",
        "category": "Program Execution 736.json"
    },
    {
        "instruction": "In this task, we have Spanish and Catalan tweets for automatic stance detection. The data has three labels Against, Favor, and Neutral which express the stance towards the target -independence of Catalonia. If the tweet criticizes the independence of Catalonia then it's 'Against' and if the tweets support it then it will be labeled as 'Favor' also if the tweets state information or news  rather than stating opinion then it will be characterized as 'Neutral'.",
        "input": "Tweet: @LluisCarrasco @3gerardpique @EnricMillo 47% del poble dir\u00e0s",
        "output": "Against",
        "category": "Stance Detection 739.json"
    },
    {
        "instruction": "This task is about writing a correct answer for the reading comprehension task. Based on the information provided in a given passage, you should identify the shortest continuous text span from the passage that serves as an answer to the given question. Avoid answers that are incorrect or provides incomplete justification for the question.",
        "input": "Passage: Further problems hampered the Arctic project after the commencement of drilling in 2012, as Shell dealt with a series of issues that involved air permits, Coast Guard certification of a marine vessel and severe damage to essential oil-spill equipment. Additionally, difficult weather conditions resulted in the delay of drilling during mid-2012 and the already dire situation was exacerbated by the \"Kulluk\" incident at the end of the year. Royal Dutch Shell had invested nearly US$5 billion by this stage of the project. Question: What conditions caused the delay of drilling in mid-2012?",
        "output": "difficult weather",
        "category": "Question Answering 74.json"
    },
    {
        "instruction": "You are given a paragraph (Passage), a question (Question) and two answer options (Option1 and Option2). Your task is to find the correct answer (and return the string of the correct option, not option1/2) for the given question from the given options and based on the given passage. Answer of the question can be found directly from the passage.",
        "input": "Passage: After I finished eating dinner , I began to feel very , very sleepy . Before I go to bed , though , I have to brush my teeth . I walked up to the bathroom , grabbed my toothbrush from the shelf on the wall , and ran it quickly under cold water . First , I opened my mouth wide and ran the brush along my bottom teeth , humming to myself while I did so . Once the tops of the bottoms of my teeth were cleaned , I made sure to reach my brush around to the back of my teeth and scrubbed those until they were clean , too . Then it was time for the top of my teeth , repeating this process on top until I am satisfied . Sometimes , I need to add a little more toothpaste to my brush , and then I clamp my teeth shut and begin to scrub my teeth , moving the brush in small circles all over . I spit out all the extra foamy toothpaste and rinse my mouth until it is clean . Question: What did they start brushing away at? Option1: wall Option2: teeth",
        "output": "teeth",
        "category": "Question Answering 743.json"
    },
    {
        "instruction": "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.",
        "input": "Prosecution Drug Treatment Alternative to Prison Act of 2001 - Amends the Omnibus Crime Control and Safe Streets Act of 1968 to authorize the Attorney General to make grants to State or local prosecutors for the purpose of developing, implementing, or expanding drug treatment alternative to prison programs under which eligible offenders, as an alternative to incarceration, shall be sentenced to or placed with a licensed, long term, drug free residential substance abuse treatment provider.",
        "output": "A bill to establish grants for drug treatment alternative to prison programs administered by State or local prosecutors.",
        "category": "Title Generation 752.json"
    },
    {
        "instruction": "You are given a paragraph (Passage), a question (Question) and two answer options (Option1 and Option2). Your task is to choose the correct answer to the question based on the passage. Answer of the question cannot be found directly from the passage, it is indirectly indicated in the passage. Do not answer with words other than the two options, and do not answer with option titles(e.g. \"option1\" or \"1\" are not acceptable answers.)",
        "input": "Passage: My family and I took a trip to Hawaii . On the island that we were on , we found a shrine that had some koi fish in a pond . When we went there , we brought some bread along with us that we could go and give to the fish that were just swimming around . I threw the pieces in the pond , even though I would have liked to eat them . The bread would settle on the surface of the water and the fish would swim up to go and eat the little pieces of bread . The fish were really excited to eat something that they may have never eaten before . We took the rest of the bread and put it in the pond for the fish to eat as we were leaving . Question: What did the person break it up with? Option1: pond Option2: hands",
        "output": "hands",
        "category": "Question Answering 753.json"
    },
    {
        "instruction": "In this task, you are given Wikipedia articles on a range of topics as passages and a question from the passage. We ask you to answer the question by classifying the answer as 0 (False) or 1 (True)",
        "input": "Passage: The Coroner -- The BBC announced on 2 March 2017 that there would be no further series.\nQuestion: will there be a second series of the coroner",
        "output": "0",
        "category": "Question Answering 755.json"
    },
    {
        "instruction": "You will be given a text in the Russian language, and you should classify the given input text to one of the emotion labels from this list of emotion labels- ['joy', 'sadness', 'surprise', 'fear', 'anger']. Make sure your output label (i) is strictly present in the given list of emotion labels. (ii) is unambiguous.",
        "input": "\u041a\u0430\u0440\u0442\u0438\u043d\u043a\u0430 \u0437\u0430\u0446\u0435\u043f\u0438\u043b\u0430 , \u0441\u0443\u0440\u043e\u0432\u0430\u044f \u0442\u0430\u043a\u0430\u044f , \u0434\u0430 \u0438 \u0430\u043a\u0442\u0435\u0440 \u043a\u0440\u0443\u0442\u043e\u0439 \u0438\u0433\u0440\u0430\u0435\u0442 , \u043a\u0430\u043a \u043f\u043e\u0442\u043e\u043c \u0432\u044b\u044f\u0441\u043d\u0438\u043b\u043e\u0441\u044c \u044d\u0442\u043e \u041a\u043b\u0430\u0439\u0432 \u041e\u0443\u044d\u043d .",
        "output": "joy",
        "category": "Sentiment Analysis 756.json"
    },
    {
        "instruction": "You will be given a text in Russian language which contain different emotion labels from the list - ['joy', ' sadness', 'surprise', 'fear', 'anger']. You need to output the incorrect emotion label, which is irrelevant to the input text. Your answer (i) should contain only one emotion label (ii) should be unambiguous.",
        "input": "\u042f \u0443\u0436\u0435 , \u043f\u0440\u0435\u0434\u0432\u043a\u0443\u0448\u0430\u044f , \u0434\u043e\u043b\u0433\u0438\u0439 \u0438 \u043c\u0443\u0447\u0438\u0442\u0435\u043b\u044c\u043d\u044b\u0439 \u043f\u0440\u043e\u0446\u0435\u0441\u0441 , \u0433\u043e\u0442\u043e\u0432\u0438\u043b\u0430\u0441\u044c \u043c\u043e\u0440\u0430\u043b\u044c\u043d\u043e .",
        "output": "anger",
        "category": "Wrong Candidate Generation 757.json"
    },
    {
        "instruction": "Given a math problem with context and a question and 5 answer choices, the task is to provide the correct answer choice based on the problem. You must choose one of the given answer choices by letter: a, b, c, d, or e; anything else is invalid.",
        "input": "Problem: a class of boys stands in a single line, one boy is 19 th in order from both the ends, how many boys are there in the class ?\nOptions: a. 37, b. 38, c. 27, d. 29, e. 11",
        "output": "a",
        "category": "Question Answering 767.json"
    },
    {
        "instruction": "This task is about translating a given English language sentence to Yoruba language.",
        "input": "We are confident that Jehovah will continue to bring \u2018comfort to all who mourn\u2019 during this difficult time.\u2014Isaiah 61:1, 2.",
        "output": "\u00d3 d\u00e1 wa l\u00f3j\u00fa p\u00e9 J\u00e8h\u00f3f\u00e0 \u00f2 n\u00ed y\u00e9\u00e9 \u2018tu gbogbo \u00e0w\u1ecdn t\u00f3 \u0144 \u1e63\u1ecd\u0300f\u1ecd\u0300 n\u00edn\u00fa\u2019 l\u00e1s\u00eck\u00f2 t\u00ed n\u01f9kan nira y\u00ec\u00ed.\u200b\u2014A\u00eds\u00e1y\u00e0 61:1, 2.",
        "category": "Translation 769.json"
    },
    {
        "instruction": "In this task, you are given inputs i and A, where i is an integer and A is a list. You need to list all the elements of A preceding the last i elements. i will always have a value less than the length of A.",
        "input": "3, ['q', 'z', '7729', 'N', 'O', '9971', 'R', 'e', '8359', '3029', '8271', '7597', '9901', '7543', 'r', 'm', 'T', 'r', '6177', '4621', '8711', 'y', 'u', '9017']",
        "output": "q, z, 7729, N, O, 9971, R, e, 8359, 3029, 8271, 7597, 9901, 7543, r, m, T, r, 6177, 4621, 8711",
        "category": "Program Execution 77.json"
    },
    {
        "instruction": "This task is about translating a given Yoruba language sentence to English.",
        "input": "\u00c0m\u1ecd\u0301 n\u00ed b\u00e1y\u00ec\u00ed, \u00f3 ti w\u00e1 d\u00e1 mi l\u00f3j\u00fa p\u00e9 J\u00e8h\u00f3f\u00e0 \u00e0ti \u00e8t\u00f2 r\u1eb9\u0300 \u00f2 n\u00ed fi m\u00ed s\u00edl\u1eb9\u0300, k\u00f3d\u00e0 t\u00ed mo b\u00e1 w\u00e0 l\u1eb9\u0301w\u1ecd\u0300n.",
        "output": "I now have confidence that I will receive the support of Jehovah and his organization, even if I am in prison.",
        "category": "Translation 770.json"
    },
    {
        "instruction": "This task is about translating a given English language sentence to French.",
        "input": "Religious person is also seeking to find less than",
        "output": "Religious person is also seeking to find less than",
        "category": "Translation 771.json"
    },
    {
        "instruction": "This task is about translating a given French language sentence to English.",
        "input": "Une f\u00eate o\u00f9 les gens \u00e9taient pr\u00e9sents, non seulement de Puno, mais du pays et d'autres pays, ils \u00e9taient pr\u00e9sents.",
        "output": "A party where people were present, not only from Puno, but people from other parts of the country and from other countries, were present.",
        "category": "Translation 773.json"
    },
    {
        "instruction": "This task is about translating a given English language sentence to Spanish.",
        "input": "So the question is these numbers aren't really getting close to anything in particular.",
        "output": "F de 0,001, que es como seno de 1000, bueno eso es 0.8 y algunos m\u00e1s, \u00bfverdad? As\u00ed que la pregunta es estos n\u00fameros no son realmente acercarse a nada en particular.",
        "category": "Translation 774.json"
    },
    {
        "instruction": "This task is about translating a given Spanish language sentence to English.",
        "input": "hizo eso por nosotros, sin pensarlo dos veces",
        "output": "\u0394\u03b5\u03bd \u03ae\u03c4\u03b1\u03bd \u03c6\u03b9\u03bb\u03b9\u03ba\u03cc;",
        "category": "Translation 775.json"
    },
    {
        "instruction": "In this task, you are presented with a term, a question, and a yes/no answer. For context, the term is associated with a short description. Write the simple facts one needs to know in order to answer the given question. The facts should be easily found on the web (e.g. mentioned in a Wikipedia page)",
        "input": "Term: Jimmy Wales, Description: Wikipedia co-founder, Question: Did Jimmy Wales go to the same university as Bo Jackson?, Answer:Yes",
        "output": "Fact1: Bo Jackson went to Auburn. Fact2: Jimmy Wales went to Auburn. ",
        "category": "Misc. 776.json"
    },
    {
        "instruction": "In this task you will be given a list of strings and you need to concatenate them.",
        "input": "['w', 'W', 'bidding.', 'J', 'M']",
        "output": "wWbidding.JM",
        "category": "Program Execution 78.json"
    },
    {
        "instruction": "You are given a short text as a title. Your task is to generate a poem as output that is related to the given title and should feel like written by kids. The output should be a run-on sentence (two or more complete sentences connected without any punctuation). The poem should not be too long or too complex, because it should feel like it is written by younger person without high level of literature education.",
        "input": "True  Love",
        "output": "true love be something everybody want but when people ca n't find true love they think they be on a wild goose chase when you find true love you know he or she be the right person and if they dump you and you still love'em but you have ask them out again but they say no wait a while and ask them agian if they still say no just look for someone else",
        "category": "Poem Generation 782.json"
    },
    {
        "instruction": "You are given a short poem which is written by a kid. Your task is to predict if the kid is in elementary school or high school. Anyone who is from grade 1st to 6th-grade will be considered as in elementary school, and 7th to 12th-grade kids will be considered as in high school. There are only two possible outputs, i.e., elementary and high. All inputs have at least one output and it cannot have both categories at a time.",
        "input": "stripe of red and white and star in a sea of blue i 'm proud to be an american to be free a me and you we 're protect by veteran every single day and night they work hard to protect u they fight with all their might american have right to live freely everyday to have their own opinion and to have their religious way we have many rule but they keep u safe and strong the government will help u to choose from right or wrong we 're free to be what we wish to a teacher doctor or vet we have a choice that ca n't be change unless our goal be n't meet i 'm proud to be an american to live my very own way i 'm proud to be an american each and every day",
        "output": "elementary",
        "category": "Text Categorization 783.json"
    },
    {
        "instruction": "In this task the focus is on physical knowledge about the world. Given the provided goal task in the input, describe a process that would lead to the asked outcome. This process often involves physical motions with objects, such as moving them, arranging them in a certain way, mixing them, shaking them, etc. ",
        "input": "cool dog off",
        "output": "Use a hand towel or a bath towel that has been dampened and kept in the freezer , rub the towel all over the dog's body",
        "category": "Question Answering 79.json"
    },
    {
        "instruction": "The task is to generate the correct answer for a given math problem.",
        "input": "Problem: the h . c . f of two numbers is 23 and the other two factors of their l . c . m are 14 and 15 . the larger of the two numbers is :",
        "output": "345",
        "category": "Question Answering 793.json"
    },
    {
        "instruction": "In this task you will be given a process, and a question. The process contains a sequence of steps that happen in order. The question asks about the effect of a certain event on another event. If the first event has a positive effect on the second event, answer with \"for\", if it has a negative effect, answer with \"against\". If there's no causal relationship between the two, answer with \"none\".",
        "input": "Process:  -Particles in the environment interact with rocks -The particles remove small pieces of the rock each time they touch the rocks -The particles continue to hit, brush against, or grow against the rocks -The rock eventually is broken apart by this contact -The pieces of the rock are now small rocks -The rock pieces are worn away into smaller and smaller pieces by the same forces -\n Question: What is the effect of animals land on the rocks on less small rocks.?",
        "output": "against",
        "category": "Question Answering 794.json"
    },
    {
        "instruction": "You will be given one or more triples. The second part of each triple shows the relation between the first and the third element. Your task is to write a simple and short piece of text (sentence(s)) that describes the triples in natural language.",
        "input": "Philippines | language | Arabic\nPhilippines | ethnicGroup | Zamboangans\nPhilippines | officialLanguage | Philippine_English\nBatchoy | country | Philippines\nPhilippines | ethnicGroup | Chinese_Filipino",
        "output": "Philippines is the country the dish Batchoy comes from. Ethnic groups there include Zamboangans and Chinese Filipino, and languages spoken are English (official) and Arabic., Philippines is the country Batchoy comes from. The country's ethnic groups include Chinese Filipino and the Zamboangans. English is the official language but Arabic is also spoken there., Batchoy comes from Philippino (Arabic) and English speaking speaking Philippines. Philippines is also home to Chinese Filipino's and Zamboangans.",
        "category": "Data to Text 795.json"
    },
    {
        "instruction": "Your task is to generate the next utterance in a given dialogue. You will be given a few sentences describing the personality of the person who is making the dialogue, and a history of the dialogue after that. Each line in the history is said by one of the two participants in the conversation.",
        "input": "Personality: I want to climb mount everest.\nI have shot a lion.\nI cry when I watch gone with the wind.\nI like to play with clay models.\nI'm not a good artist.\nChat history: -I'm a hot mess... wanna hear how?\n -Yeah sure.\n -I hear voices.\n -Anything else?\n -I like to argue... with myself.\n -So you must be good at debate.\n -I mostly just argue about how hot the pool boy is.\n -That is usually hotly debated. I cry when I watch movies.\n -Let me guess... gone with the wind gets ya?\n -Aw, how did you know? Cries and cries and cries.\n -I told you... I hear voices.",
        "output": "I want to hear what your voices say... do they think I can climb mt. Everest?",
        "category": "Dialogue Generation 796.json"
    },
    {
        "instruction": "You 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.",
        "input": "Personality: I m from Seattle.\nI work in public relations.\nMy parents raised me as a buddhist.\nI'm a vegan.\nMy favorite band is bon over.\nChat history: -Hello how are you doing today?\n -I am doing amazing so far.\n -Great, I am just spending time with my 8 grandchildren since I am retired.\n -That sounds like a great job.\n -It is, I like staying very active to keep in good health.\n -Healthy is important these days.\n -Yes, it is. Tell me about yourself.\n -Well I am amazing, also a vegan.\n -You sound amazing! Vegan, that is a hard lifestyle choice!\nCandidates 1) Do you like beans at all. 2) Nah not married. I am only seven. 3) I suffer from diabetes so kids could be rough on that front. 4) I am kind of a big deal.",
        "output": "I am kind of a big deal.",
        "category": "Dialogue Generation 798.json"
    },
    {
        "instruction": "You will be asked how to do a certain task. You should describe a physical process that does not lead to the asked outcome, yet it is closely related to it (i.e., it should use the words that are provided in the input). The physical process can be moving something, arranging something in a certain way, mixing things, shaking them, etc. To make sure that the generated process does not lead to the asked outcome, you can introduce objects or events unrelated to the context of the question e.g. 'cleaning the keyboard by making an elephant sit on them'; or you can create contradictory statements e.g. 'drying wet keyboards with running water'. In your responses, avoid typos and misspellings.",
        "input": "How to carefully water a plant?",
        "output": "Pour water over the top of the plant into the soil and wait until the water disappears and is saturated then continue",
        "category": "Wrong Candidate Generation 80.json"
    },
    {
        "instruction": "This is a paraphrasing task. In this task, you're given a sentence and your task is to generate another sentence which express same meaning as the input using different words.",
        "input": "besides , i would n't want to take food out of the mouths of all those tapeworms you 're feeding .",
        "output": "besides , i would n't take food from those tapeworms you do .",
        "category": "Paraphrasing 804.json"
    },
    {
        "instruction": "You are given a question or fill-in-the-blank question, two answer options (Option1 and Option2) and an Explanation. Your task is to find the correct answer (return the string of the correct option, not option1/2) for the given question from the given options and using explanation.",
        "input": "Question: Tina had a large rock on the beach. Rich had a large rock 10 miles inland. The person with the rock that has more effect on the tides is \n Option1: Rich \n Option2: Tina \n Explanation: The Moon has a greater effect on the tides because, although it is much smaller than the Sun, it is much closer.",
        "output": "Tina",
        "category": "Question Answering 805.json"
    },
    {
        "instruction": "In this task, you're given a pair of sentences, sentence 1 and sentence 2, that agree with each other. Your job is to alter sentence 2 so that the pair neither agree nor contradict each other. Generated sentences must be short, with less than 15 words. New information can be introduced. Avoid using pronouns to confuse the subject of the sentence.",
        "input": "Sentence 1: Three men are standing on a sidewalk in the daytime talking to each other. Sentence 2: Some men are talking to each other.",
        "output": "Some men are discussing how to kidnap people.",
        "category": "Sentence Composition 812.json"
    },
    {
        "instruction": "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.",
        "input": "Sentence 1: A group of people standing in front of a food stamp buying food. Sentence 2: A guy rides his bike through the Farmer's Market.",
        "output": "A group buys food at a Farmer's Market.",
        "category": "Sentence Composition 813.json"
    },
    {
        "instruction": "In this task, you're given a pair of sentences, sentence 1 and sentence 2, that contradict each other. Your job is to alter sentence 2 so that the pair agree with 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.",
        "input": "Sentence 1: A young girl in a pink and white outfit is dancing on stage holding a microphone. Sentence 2: A girl whispers a secret to her friend.",
        "output": "A child performing.",
        "category": "Sentence Composition 814.json"
    },
    {
        "instruction": "In this task, you're given a pair of sentences, sentence 1 and sentence 2, that agree with each other. Your job is to alter sentence 2 so that the pair 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.",
        "input": "Sentence 1: A man is sitting on a stoop in front of a door next to an icon. Sentence 2: A man is on a porch.",
        "output": "A man is standing in the road.",
        "category": "Sentence Composition 815.json"
    },
    {
        "instruction": "In this task, you're given a pair of sentences, sentence 1 and sentence 2, that neither agree with nor contradict each other. Your job is to alter sentence 2 so that the pair clearly agree with 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.",
        "input": "Sentence 1: A group of children are playing on swings. Sentence 2: The children are playing on swings outside.",
        "output": "There are children playing.",
        "category": "Sentence Composition 816.json"
    },
    {
        "instruction": "In this task, you're given a pair of sentences, sentence 1 and sentence 2, that neither agree with nor contradict each other. Your job is to alter sentence 2 so that the pair clearly 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.",
        "input": "Sentence 1: A girl bounces upside down on her head on a trampoline. Sentence 2: The girls is getting hurt.",
        "output": "The girl is doing a trick on the trampoline.",
        "category": "Sentence Composition 817.json"
    },
    {
        "instruction": "In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to choose whether the two sentences clearly agree (entailment)/disagree (contradiction) with each other, or if this cannot be determined (neutral). Your answer must be in the form of the letters E, C, and N respectively.",
        "input": "Sentence 1: an old lady and a child are sitting at an ornate green table whilst being served by food by an African person. Sentence 2: A old lady is taking her grandson out to eat.",
        "output": "N",
        "category": "Textual Entailment 818.json"
    },
    {
        "instruction": "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.",
        "input": "David William Donald Cameron ( ; born 9 October 1966) is a British politician who was Prime Minister of the United Kingdom from 2010 to 2016 and Leader of the Conservative Party from 2005 to 2016. He was Member of Parliament (MP) for Witney from 2001 to 2016. Cameron identifies as a One-Nation Conservative, and has been associated with both economically liberal and socially liberal policies. Question: What British Politician, who was the Prime Minister of the Unted Kingdom, was the person who forced a resignation from PAtrick Mercer? Answer: David Cameron",
        "output": "David William Donald Cameron  ; born 9 October 1966 is a British politician who was Prime Minister of the United Kingdom from 2010 to 2016 and Leader of the Conservative Party from 2005 to 2016.",
        "category": "Explanation 820.json"
    },
    {
        "instruction": "In this task, you are given a text from tweets. Your task is to classify given tweet text into two categories: 1) positive, and 2) negative based on its content.",
        "input": "the most beutiful day this spring....and I'm in front of the laptop ",
        "output": "negative",
        "category": "Sentiment Analysis 823.json"
    },
    {
        "instruction": "In this task, you are given a text from tweets and a boolean question whether this tweet has positive sentiment or negative sentiment. Your task is to generate answer \"yes\" when the tweet has that particular sentiment, otherwise generate answer \"no\".",
        "input": "Tweet: Coachella Tonight!! Tropical.  Question: is it a positive tweet?",
        "output": "yes",
        "category": "Sentiment Analysis 824.json"
    },
    {
        "instruction": "In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to write a single word that describes the genre that the two sentences belong to, such as face-to-face, government, letters, 9/11, slate, telephone, travel, verbatim, oup, fiction.",
        "input": "Sentence 1: After the Madness reads like going to court feels. Sentence 2: Reading \"After the Madness\" feels like going to court.",
        "output": "slate",
        "category": "Text Categorization 825.json"
    },
    {
        "instruction": "In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to classify the genre of the sentences from the 10 options displayed. Indicate your answer by entering the number of the choice as 1-10.",
        "input": "Sentence 1: Spectator  Ireland's most famous sport, horse racing, takes place at Leopardstown; The Curragh is the headquarters of flat racing, and the home of National Hunt racing is Punchestown in Kildare. Sentence 2: Ireland does not host any horse racing events. Choices: 1. FACE-TO-FACE, 2. GOVERNMENT, 3. LETTERS, 4. 9/11, 5. SLATE, 6. TELEPHONE, 7. TRAVEL, 8. VERBATIM, 9. OUP, 10. FICTION.",
        "output": "6",
        "category": "Text Categorization 826.json"
    },
    {
        "instruction": "In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to determine if the two sentences clearly agree/disagree with each other, or if this can't be determined. Indicate your answer as yes or no respectively.",
        "input": "Sentence 1: If the mandate does not specify a committee, GAO will work with the committees of jurisdiction (majority and minority) as set forth in Senate and House rules and any other committees and/or Members identified by the committees of jurisdiction. Sentence 2: The Senate and House rules do not apply",
        "output": "yes",
        "category": "Textual Entailment 827.json"
    },
    {
        "instruction": "In this task, you're given a statement and three sentences as choices. Your job is to determine which sentence can be inferred from the statement. Incorrect choices change the meaning in important ways or have details that are not mentioned in the statement. Indicate your answer as 1,2, or 3 corresponding to the choice number of the selected sentence.",
        "input": "Statement: Outside Baillif is the best preserved of the sugar-mill watchtowers erected by the famous militant priest, Pyre Labat . Choices:  1. Famous militant priest, Pyre, Labat, had sugar-mill watchtowers erected. 2. Baillif is home to the most sugar-mills in the world. 3. Pyre Labat was known primarily for his ditch-digging skills.",
        "output": "1",
        "category": "Textual Entailment 828.json"
    },
    {
        "instruction": "In this task, you're given a statement and three sentences as choices. Your job is to determine the neutral choice based on your inference from the statement and your commonsense knowledge. The neutral choice is a sentence that neither agrees nor disagrees with the statement. Indicate your answer as '1', '2', or '3', corresponding to the choice number of the selected sentence. If sentence X agrees with sentence Y, one's correctness follows from the other one. If sentence X disagrees with sentence Y, they can not be correct at the same time.",
        "input": "Statement: To the degree that we regard them as goads to compassion and involvement (as in Bosnia or the Middle East), showing them is a purported moral good. Choices: 1. To the degree we regard them as goads of compassion and involvement than showing them is purportedly a moral good because it gives them a positive image. 2. To the degree we regard them as goads of compassion and involvement than showing them is purportedly a moral good. 3. To the degree we regard them as goads of compassion and involvement than showing them is purportedly a moral evil.",
        "output": "1",
        "category": "Textual Entailment 829.json"
    },
    {
        "instruction": "In this task, you're given a statement, and three sentences as choices. Your job is to determine which sentence clearly disagrees with the statement. Indicate your answer as '1', '2', or '3' corresponding to the choice number of the selected sentence.",
        "input": "Statement: yeah sure but they played like professionals exactly right Choices:  1. It was embarrassing seeing them be so unprofessional. 2. Yes, they played like the pros they are. 3. I was proud and impressed watching them get their professionalism on!",
        "output": "1",
        "category": "Textual Entailment 830.json"
    },
    {
        "instruction": "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.",
        "input": "Statement: This has a multiplier  one lawyer trains 20 social workers, each of whom helps 50 clients, resulting in 1,000 people and families getting legal information, materials or referrals they might otherwise not have had.\nLabel: contradiction.\nGenre: government.",
        "output": "The lawyer is incompetent and didn't help anyone.",
        "category": "Sentence Composition 831.json"
    },
    {
        "instruction": "In this task, you're given two sentences, sentence 1 and sentence 2, and the genre they belong to. Your job is to determine if the two sentences belong to the same genre or not. Indicate your answer with Y and N respectively. Genres available include: face-to-face, government, letters, 9/11, slate, telephone, travel, verbatim, oup, fiction. Sentences belonging to 'face-to-face' genres relate to conversations or dialogues, 'government' encompasses information released from public government websites, 'letters' refers to any written work for philanthropic fundraising, '9/11' relates to information pertaining to the 9/11 attacks, 'oup' includes non-fiction works on the textile industry and child development, 'slate' refers to any cultural topic that appears in the slate magazine, 'telephone' includes telephonic dialogue, 'travel' deals with information in travel guides, 'verbatim' includes short posts regarding linguistics, and 'fiction' includes popular works of fiction like 'The Secret Adversary' etc.",
        "input": "Sentence 1: I turned and as I left I saw Susan for the first time. Sentence 2: It was the first time I looked at Susan. Genre: fiction.",
        "output": "Y",
        "category": "Text Categorization 832.json"
    },
    {
        "instruction": "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.",
        "input": "[17, 9, 67, 95]",
        "output": "[17, 9, 67, 95]",
        "category": "Program Execution 833.json"
    },
    {
        "instruction": "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 two, if the element is odd you should multiply by three then add one. The output should be a list of integers that is the result of applying that logic to the input list.",
        "input": "[72, 29, 49]",
        "output": "[36, 88, 148]",
        "category": "Program Execution 834.json"
    },
    {
        "instruction": "In this task, you are given a list. This list contains many lists of integers. The list is several items written within a []. Your task is to find the maximum number among the members of each inner list. The output should be a list comprised of the maximums with the same order as the internal lists.",
        "input": "[[42, 86, -134, 77], [-175, 33, -14, 21, -83], [-16, -66, -132, -60], [-125, 46], [-28, 59, 70, 57, -161, -86, -91], [-35, 98, -179, -67, 78], [-176, -102, 41], [-69, 1], [-13, 90, -168]]",
        "output": "[86, 33, -16, 46, 70, 98, 41, 1, 90]",
        "category": "Program Execution 835.json"
    },
    {
        "instruction": "In this task, you will be given a list.  The list is several integers and letters separated with a comma, written within a []. You can create new lists by dropping one of the items in the input list. Your task is to write a list containing all the possible lists you can make by dropping one item from the input list. For example, if the input list contains two items, you can drop one of the items each time. So the output should be a list comprising two inner lists that you have created by decreasing the items.",
        "input": "['Q', 't', '2', 'A', 'O', '7', 'P']",
        "output": "[['Q', 't', '2', 'A', 'O', '7'], ['Q', 't', '2', 'A', 'O', 'P'], ['Q', 't', '2', 'A', '7', 'P'], ['Q', 't', '2', 'O', '7', 'P'], ['Q', 't', 'A', 'O', '7', 'P'], ['Q', '2', 'A', 'O', '7', 'P'], ['t', '2', 'A', 'O', '7', 'P']]",
        "category": "Program Execution 836.json"
    },
    {
        "instruction": "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.",
        "input": "7745 + 5832 - 4271 - 4750 + 8466 - 2676 + 6861",
        "output": "-1717",
        "category": "Mathematics 84.json"
    },
    {
        "instruction": "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.",
        "input": "Title: Popcorn Disaster. Sentence 1: Bill's parents went to the movies, leaving him at home. Sentence 2: He decided to create his own movie experience, including popcorn. Sentence 3: He heated oil on the stove before adding the kernels. Sentence 4: It began to pop and didn't stop. Choices: a. Andy was feeling the unemployment blues pretty bad. b. Before he knew it popcorn was flowing out of the pot.",
        "output": "b",
        "category": "Text Completion 841.json"
    },
    {
        "instruction": "In this task, you're given the title of a five-sentence story, the first four sentences, and two options for the fifth sentence as a and b. Your job is to pick the sentence option that does not connect with the rest of the story, indicating your choice as 'a' or 'b'. If both sentences are plausible, pick the one that makes less sense.",
        "input": "Title: App Updates. Sentence 1: Nina needed to access her phone as quickly as possible. Sentence 2: She was about to make an urgent call when something popped up. Sentence 3: Suddenly dozens of apps began updating themselves. Sentence 4: By the time the downloading stopped it was too late. Choices: a. Tony decided to quit his job right then and there. b. Nina had to find a different phone to make her call.",
        "output": "a",
        "category": "Text Completion 842.json"
    },
    {
        "instruction": "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.",
        "input": "Title: Erased Pictures. Sentence 1: Oliver was taking pictures of his family at the beach. Sentence 2: When they got back into the car, Oliver went to look at the pictures. Sentence 3: Oliver accidentally erased the photos. Sentence 4: Oliver couldn't get the pictures back.",
        "output": "After I finished my ice cream, my stomach upsetted me.",
        "category": "Text Completion 843.json"
    },
    {
        "instruction": "In this task, you're given the title of a five-sentence story and the first four sentences. Your job is to write the last sentence of the story such that it seamlessly connects with the rest of the story.",
        "input": "Title: Two Siblings. Sentence 1: Kia had been excited when she discovered her mom was having a baby. Sentence 2: She was thrilled to have a little brother or sister! Sentence 3: Her parents wouldn't tell her the gender, saying it was a surprise. Sentence 4: When they returned from the hospital, Kia was indeed surprised.",
        "output": "She had TWIN siblings - a brother AND a sister!",
        "category": "Text Completion 844.json"
    },
    {
        "instruction": "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'.",
        "input": "Title: Javier Brushes His Teeth. Sentence 1: He gets up and brushes his teeth. Sentence 2: Then he returns to bed. Sentence 3: He knows he should brush them before going to bed. Sentence 4: Lying in bed, Javier remembers that he didn't brush his teeth. Sentence 5: Javier is glad he brushed his teeth.",
        "output": "43125",
        "category": "Sentence Ordering 845.json"
    },
    {
        "instruction": "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.",
        "input": "Title: Escape. Sentence 1: Jimmy Jackson was a prison guard. Sentence 2: One day he was asked to watch over a high security offender. Sentence 3: He spent most of the day monitoring him closely. Sentence 4: The prisoner was hungry too, so he got a burger and was recaptured. Sentence 5: Until the prisoner escaped as he was eating lunch.",
        "output": "54",
        "category": "Sentence Ordering 846.json"
    },
    {
        "instruction": "In this task, you're given five sentences, numbered 1 through 5. Your job is to generate a title for the story that makes complete sense. The title must be short, with less than three words, use simple language, and include the main topic of the story.",
        "input": "Sentence 1: Jason felt bad about the condition of his community. Sentence 2: He decided to do something about it. Sentence 3: Jason ran for city councilman. Sentence 4: He ran a good campaign and told people he really wanted to help. Sentence 5: Jason won the election and became city councilman!",
        "output": "Councilman",
        "category": "Title Generation 847.json"
    },
    {
        "instruction": "In this task, you're given five sentences, numbered 1 through 5, and two options a and b for possible titles for the story. Your job is to choose the title that better fits the story. Indicate your choice by 'a' or 'b'.",
        "input": "Sentence 1: Fred and Allie went to the fair together. Sentence 2: Fred won Allie a stuffed frog. Sentence 3: She thought it was cute. Sentence 4: She would have it forever. Sentence 5: It was there that he proposed to her. Choices: a. Winning a frog. b. Good deal on the home.",
        "output": "a",
        "category": "Title Generation 848.json"
    },
    {
        "instruction": "In this task, you're given the title and three arbitrary sentences out of a five-sentence story. You are also given three additional sentence options, a, b, and c, that may or may not belong to the story. Your job is to pick the two options that seamlessly connect with the rest of the story; note that the selected choices may fit into the story at any point. Indicate your selected choices in order, i.e., as 'ab'/'bc'/'ac' and not as 'ba'/'ca'/'cb'. If options are equally plausible, pick the ones that make more sense.",
        "input": "Title: The car was totaled. Trevor's mom was furious. He had to pay to repair the car and the pole. Choices: a. Trevor was driving his car. b. He crashed into a pole. c. Jimmy's boss decided to close the restaurant for the day.",
        "output": "ab",
        "category": "Text Completion 849.json"
    },
    {
        "instruction": "In this task you will be given an arithmetic operation in Italian and you have to find its answer. The operations 'addition' and 'subtraction' have been replaced with their italian translations i.e you need to perform addition when you see 'aggiunta' and subtraction in case of 'sottrazione'.",
        "input": "6682 aggiunta 8714 sottrazione 2141 aggiunta 7876 aggiunta 8194",
        "output": "29325",
        "category": "Mathematics 85.json"
    },
    {
        "instruction": "In this task, you're given the title and three arbitrary sentences out of a five-sentence story. You are also given three additional sentence options, a, b, and c, that may or may not belong to the story. Your job is to pick the two options that seamlessly connect with the rest of the story and their positions in the sentence order of the story; note that the selected choices may fit into the story at any point. Your answer must be in the form of '2a, 5b', where '2a' means the candidate sentence 'a' will be inserted as the 2nd sentence in the story. The answer must also be in the order of the selected choices, i.e., '2a, 5b' is allowed, and '5b, 2a' is not allowed. If options are equally plausible, pick the ones that make more sense.",
        "input": "Title: Betsy could not sleep at night. She had a bad feeling. She went to the kitchen to grab some snack. Choices: a. She finally gave up and went home. b. She found out her kitchen was flooded. c. She had to call 911.",
        "output": "4b, 5c",
        "category": "Text Completion 850.json"
    },
    {
        "instruction": "In this task, you are given a question and answer for that. The answer will fill in the blank or will complete the unfinished question. Your task is to provide an explanation based on the given question or fill-in-the-blank statement, and answer.",
        "input": "Question: Mona is sitting at the beach watching the waves. If the wind starts blowing faster, what will happen to the size of the waves? \n Answer: increase",
        "output": "The faster, longer, and farther the wind blows, the bigger the waves are.",
        "category": "Explanation 851.json"
    },
    {
        "instruction": "In this task, you are given an ambiguous question/query (which can be answered in more than one way) and a clarification statement to understand the query more precisely. Your task to classify that if the given clarification accurately clarifies the given query or not and based on that provide 'Yes' or 'No'.",
        "input": "Query: What is martha stewart and imclone? \n Clarification: how experienced are you at sewing",
        "output": "No",
        "category": "Question Understanding 855.json"
    },
    {
        "instruction": "You are given a science question (easy-level) and four answer options (associated with \"A\", \"B\", \"C\", \"D\"). Your task is to find the correct answer based on scientific facts, knowledge, and reasoning. Do not generate anything else apart from one of the following characters: 'A', 'B, 'C', 'D'. There is only one correct answer for each question.",
        "input": "Photovoltaic cells capture photons of sunlight and transform them directly into electricity. Many of Earth's other energy resources are simply transformed solar energy. Which two energy resources store energy that did not begin as solar energy?   \n (A) oil and coal (B) wind and wood (C) nuclear and geothermal (D) hydropower and natural gas",
        "output": "C",
        "category": "Question Answering 856.json"
    },
    {
        "instruction": "In this task, you're given a question, a context passage, and four options which are terms from the passage. After reading a passage, you will get a brief understanding of the terms. Your job is to determine by searching and reading further information of which term you can answer the question. Indicate your choice as 'a', 'b', 'c', or 'd'. If you think more than one option is plausible, choose the more probable option to help you answer the question.",
        "input": "Question: How many league championships have been won by the team that Harvard upset in 2014? Passage:Harvard Crimson men's basketball program represents intercollegiate men's basketball at Harvard University. The team currently competes in the Ivy League in Division I of the National Collegiate Athletic Association (NCAA) and plays home games at the Lavietes Pavilion in Boston, Massachusetts. The team appeared in the NCAA Division I Men's Basketball Tournament in 2014, where Harvard upset 5-seed Cincinnati 61\u201357 before being eliminated in the round of 32 by 4-seed Michigan State by a score of 80\u201373. In 2015, Harvard tied with Yale for the Ivy title with an 11\u20133 league record. Despite having lost to Yale 62\u201352 at Lavietes Pavilion on March 6, 2015, just eight days later Harvard won a playoff between the two at the Palestra in Philadelphia to determine the Ivy League's NCAA automatic bid by a score of 53\u201351. Harvard thereby achieved its fourth straight NCAA Tournament appearance while preventing Yale from reaching the NCAA Tournament for the first time in 53 years. Harvard was eliminated from the 2015 NCAA Tournament by UNC by a score of 67\u201365 after leading with under one minute to play in the game. \n Links: a. NCAA Division I b. Cincinnati Bearcats men's basketball c. Lavietes Pavilion d. Yale Bulldogs men's basketball",
        "output": "b",
        "category": "Question Answering 859.json"
    },
    {
        "instruction": "In this task you will be given an arithmetic operation and you have to find its answer. The operators '+' and '-' have been replaced with new symbols. Specifically, '+' has been replaced with the symbol '@' and '-' with the symbol '#'. You need to perform the operations in the given equation return the answer",
        "input": "5707 # 1540 # 8185 # 8054 @ 554",
        "output": "-11518",
        "category": "Mathematics 86.json"
    },
    {
        "instruction": "In this task, you're given a question, along with a context passage which has extra information available on certain terms mentioned in it, i.e., the proper nouns in the passage. Your job is to determine whether information from more than one term is needed to answer the question. Indicate your choice as `a` for Yes or `b` for No.",
        "input": "Question: How old was the Antartic's commander when he dropped Otto's party off at a small island? Passage:He led the 1901-1904 Swedish Antarctic Expedition, aboard the ship Antarctic. The expedition visited the Falkland Islands before the ship, commanded by seasoned Antarctic sailor Carl Anton Larsen, dropped Nordenskj\u00f6ld's party off at Snow Hill Island, a small island off the coast of the Antarctic Peninsula. Nordenski\u00f6ld overwintered at Snow Hill Island, while Antarctic returned to the Falklands. The following summer Larsen brought her south, intending to retrieve the Nordenski\u00f6ld party, but she became trapped in ice which eventually crushed her hull, forcing Larsen and his crew to overwinter in a hastily constructed shelter on Paulet Island. Larsen and Nordenskj\u00f6ld finally rendezvoused at their fall-back rescue hut at Hope Bay in late 1903, where they were picked up by the Argentine Navy corvette ARA Uruguay (commanded by Juli\u00e1n Ir\u00edzar), which had been dispatched when Antarctic had failed to make her appointed return to South America the previous year. Despite its end and the great hardships endured, the expedition was considered a scientific success, with the parties having explored much of the eastern coast of Graham Land, including Cape Longing, James Ross Island, the Joinville Island group, and the Palmer Archipelago. The expedition, which also recovered valuable geological samples and samples of marine animals, earned Nordenskj\u00f6ld lasting fame at home, but its huge cost left him greatly in debt.\n",
        "output": "b",
        "category": "Answerability Classification 860.json"
    },
    {
        "instruction": "In this task, you're given a question, along with a context passage. The passage will not have a direct answer to the question, but can include some information and a clue for the answer. Assuming you can only obtain information about one entity in the passage, your job is to determine whether information from the passage can be used to answer the question. Indicate your choice as `a` for Yes or `b` for No.",
        "input": "Question: Who was the first recipient of the award MacGraw was nominated for due to her performance in Love Story? Passage:Elizabeth Alice \"Ali\" MacGraw (born April 1, 1939) is an American actress, model, author, and animal rights activist. She first gained attention with her role in the film Goodbye, Columbus (1969), for which she won the Golden Globe Award for Most Promising Newcomer. She gained an international profile for her role in the film Love Story (1970), for which she was nominated for an Academy Award for Best Actress and won the Golden Globe Award for Best Actress in a Motion Picture \u2013 Drama. In 1972, MacGraw was voted the top female box office star in the world and was honored with a hands and footprints ceremony at Grauman's Chinese Theatre after having been in just three films. She went on to star in the popular action films The Getaway (1972) and Convoy (1978) as well as the romantic sports drama Players (1979), the comedy Just Tell Me What You Want (1980), and the historical novel-based television miniseries The Winds of War (1983). In 1991, she published an autobiography, Moving Pictures.\n",
        "output": "b",
        "category": "Answerability Classification 861.json"
    },
    {
        "instruction": "In this task, you're given a context, further information available on a particular linked term from the statement, and an answer term. Your job is to generate a question that can use the information provided to obtain the given answer. You should use the information on both context and link information to create the question. Note that the answer to the question should be exactly the given answer, and if the answer is none, the answer to the question shouldn't be obtainable from the context or linked information.",
        "input": "Context: Tasman is most well known for his time-lapse photography piece completed in 2009. Here he made a Polaroid instant film self-portrait every day for ten years and one day Link Information: Tasman discussed with Mark Metcalf how the medium also seemed fitting to when dealing with conceptual issues of memory and storytelling. Answer: 63",
        "output": "How old was the person Marc talked about time-lapse photography with when he completed his 10 year project?",
        "category": "Question Generation 863.json"
    },
    {
        "instruction": "In this task, you're given a passage, further information available on a particular linked term from the statement, and an answer term. Your job is to generate a question that can use the information provided to obtain the given answer. You should use the information on both passage and link information to create the question. Note that the answer to the question should be exactly the given answer, and if the answer is none, the answer to the question shouldn't be obtainable from the passage or linked information.",
        "input": "Passage: Kean was born September 28, 1893, in Elberon, New Jersey. His father, Hamilton Fish Kean (1862\u20131941), was a United States Senator from New Jersey and his son, Thomas Kean, served two terms as the Governor of New Jersey. Robert Kean was the great-great-grandson of John Kean, a Delegate to the Continental Congress from South Carolina (1756\u20131795). His uncle, John Kean (1852\u20131914), was also a United States Senator from New Jersey. His grandson, Thomas Kean, Jr., is presently the Minority Leader of the New Jersey State Senate. His mother, Katherine Taylor Winthrop (1866\u20131943), was a descendant of John Winthrop, a wealthy English Puritan lawyer and one of the leading figures in the founding of the Massachusetts Bay Colony, the first major settlement in what is now New England after Plymouth Colony. Winthrop led the first large wave of migrants from England in 1630 and served as governor for 12 of the colony's first 20 years of existence. Kean is also a descendant of William Livingston, the first Governor of New Jersey.\n Link Information: The New Jersey Senate was established as the upper house of the New Jersey Legislature by the Constitution of 1844, replacing the Legislative Council.  Answer: 1844",
        "output": "When was the legislative body that Robert Kean's grandson serves first established?",
        "category": "Question Generation 864.json"
    },
    {
        "instruction": "In this task, you're given a statement, 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'.",
        "input": "Context: and returned again on July 17 against the Washington Nationals. Link Information: The current NL club was founded in 1969  Question: When did the team that Bay returned against in July form?",
        "output": "Answer: 1969 ",
        "category": "Question Answering 865.json"
    },
    {
        "instruction": "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'.",
        "input": "Passage: As an amateur, Doherty won the Irish Amateur Championship twice, the World Under-21 Amateur Championship and the World Amateur Championship. Having turned professional in 1990, Doherty has won a total of six ranking tournaments, including the 1997 World Snooker Championship in which he defeated Stephen Hendry, inflicting Hendry's first loss in a world final. This made him the first player, and so far one of only two (the other being Stuart Bingham) to have been world amateur and professional champion. The following year, he came very close to breaking the Crucible curse, reaching the 1998 final where he lost out to John Higgins. He reached a third final in 2003, in which he was defeated by Mark Williams. In other triple crown events, he is a three-time UK Championship runner-up and a two-time Masters runner-up.\n Link Information: Stephen Gordon Hendry (born 13 January 1969) Question: What year was the man born who Doherty defeated in the 1997 World Snooker Championship?",
        "output": "Answer: 1969",
        "category": "Question Answering 866.json"
    },
    {
        "instruction": "In this task, you are given a context paragraph of the tweet and question. Your task is to generate right answer of given question based on given context tweet paragraph.",
        "input": "Context: Men silencing my speech silencing @RSDJulien speech about #ChokingGirlsAroundTheWorld #takedownjulienblanc Heather Marsh (@GeorgieBC) November 3, 2014 Question: who does heather want to take down?",
        "output": "julien blanc",
        "category": "Question Answering 867.json"
    },
    {
        "instruction": "In this task, you are given a context tweet and an answer. Your job is to generate a question for the given answer based on the given tweet paragraph. Note that your question should be answerable based on the given tweet, and the answer to your question should be the given answer.",
        "input": "Context: Grapes: Because of course he did (pic via @AshySkates @criseyde) \u2014 Phil Hecken (@PhilHecken) March 15, 2015 Answer: grapes",
        "output": "what fruit is mentioned in this tweet?",
        "category": "Question Generation 868.json"
    },
    {
        "instruction": "In this task, you are given a context tweet, a question and corresponding answer of given question. Your task is to classify this question-answer pair into two categories: (1) \"yes\" if the given answer is right for question, and (2) \"no\" if the given answer is wrong for question.",
        "input": "Context: I'm right where I want to be, @realDonaldTrump: Calling you out & holding you responsible for your reckless vision for America.\u2014 Elizabeth Warren (@elizabethforma) July 23, 2016 Question: what is realdonaldtrump responsible for? Answer: mike nichols",
        "output": "no",
        "category": "Answer Verification 869.json"
    },
    {
        "instruction": "The given sentence contains a typo which could be one of the following four types: (1) swapped letters of a word e.g. 'niec' is a typo of the word 'nice'. (2) missing letter in a word e.g. 'nic' is a typo of the word 'nice'. (3) extra letter in a word e.g. 'nicce' is a typo of the word 'nice'. (4) replaced letter in a word e.g 'nicr' is a typo of the word 'nice'. You need to identify the typo in the given sentence. To do this, answer with the word containing the typo.",
        "input": "A wood bench sitting in front of a tree.",
        "output": "None",
        "category": "Spelling Error Detection 87.json"
    },
    {
        "instruction": "In this task, you are given a context tweet, a question and corresponding answer of given question. Your task is to classify given passage into two categories: (1) \"yes\" if the given context is useful in answering the question, and (2) \"no\" if the given context is not useful.",
        "input": "Context: .@LaurentFabius: \"Tomorrow at 9 a.m., I will present a text that is as balanced & as ambitious as possible\" #COP21 UN Climate Action (@UNFCCC) December 11, 2015 Question: what will neymar wear for the game? Answer: boots",
        "output": "no",
        "category": "Answerability Classification 870.json"
    },
    {
        "instruction": "In this task, you are given two sets, and a question. You need to find whether an element is at the intersection of two given sets.  A Set is shown by two curly braces and comma-separated numbers inside, like {1, 2, 3}. The intersection of two given sets is the largest set which contains all the elements that are common to both sets. An element is at the intersection of two given sets, A and B, if common to both A and B. Classify your answers into 'Yes' or 'No'.",
        "input": "Set1: '{2, 3, 5, 8, 10, 11, 13, 14}', Set2: '{9, 12, 14, 15, 17, 20}'. Is the element '20' in the intersection of Set1 and Set2 ?",
        "output": "No",
        "category": "Program Execution 873.json"
    },
    {
        "instruction": "In 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\".",
        "input": "W: Did you see Mary somewhere around? M: Yes, she is in the campus bank, applying for the student's loan.",
        "output": "What was Mary doing? (A) Reading on the campus lawn. (B) Depositing money in the bank. (C) Applying for financial aid.",
        "category": "Question Generation 874.json"
    },
    {
        "instruction": "In this task, you will be shown a conversation and a question. You need to answer the question and choose the correct option based on the conversation. \"W\" and \"M\" in the conversations stand for \"woman\" and \"man\".",
        "input": "F: Do you like spring best, Jim? M: No, I like summer best because I can go swimming in summer., Question: Which is Jim's favorite season? (A) Spring. (B) Summer. (C) Winter.",
        "output": "(B) Summer.",
        "category": "Question Answering 875.json"
    },
    {
        "instruction": "In this task, positions of two consecutive words have been swapped. You need to output the position of the swaped words. e.g. in the sentence 'Seattle has nice a weather', the word 'a' and 'nice' have been swapped. These words are at 3rd and 4th position respectively. So, the output should be (3, 4). Note that the index of first word is 1.",
        "input": "A toilet sitting on a cement outside pad",
        "output": "(7, 8)",
        "category": "Grammar Error Detection 88.json"
    },
    {
        "instruction": "A ploynomial equation is a sum of terms. Here each term is either a constant number, or consists of the variable x raised to a certain power and multiplied by a number. These numbers are called weights. For example, in the polynomial: 2x^2+3x+4, the weights are: 2,3,4. You can present a polynomial with the list of its weights, for example, equation weights = [6, 4] represent the equation 6x + 4 and equation weights = [1, 3, 4] represent the equation 1x^2 + 3x + 4. In this task, you need to compute the result of a polynomial expression by substituing a given value of x in the given polynomial equation. Equation weights are given as a list.",
        "input": "x = 3, equation weights = [5, 0, 1]",
        "output": "46",
        "category": "Mathematics 89.json"
    },
    {
        "instruction": "In this task, you are given inputs 'i', 'j', and A, where 'i' and 'j' are integers and A is a list. A list is shown by two brackets and comma-separated numbers and characters inside, like ['1', '12', 'l']. You need to concatenate all elements of A from the ith element to the jth element, and then reverse the resulting string. 'i' and 'j' will be non-negative, and will always have a value less than the length of A. 'i' will always be less than 'j'. Perform the operations in order, i.e., do not reverse first and then concatenate.",
        "input": "11, 11, ['2125', 'h', '2819', '49', 'l', 't', '399', 'v', '4803', 'k', 'H', 'g', '1227', '3521', 'f', '627', 'b', 'p', '1557', 'L', 'A']",
        "output": "H",
        "category": "Program Execution 895.json"
    },
    {
        "instruction": "Given a premise, an initial context, an original ending, and a counterfactual context, the task is to generate a new story ending aligned with the counterfactual context and as close to the original ending as possible. Each instance consists of a five-sentence story. The premise is the first sentence of a story, and the second sentence, which is the initial context, provides more information about the story's context and the story's general plot. The original ending is the last three sentences of the story. Also, a counterfactual context is a slight modification to the initial context. You should write a new story ending that edits the original story ending as little as possible to regain coherence with the counterfactual context. To sum up, you should write the last three sentences of a story based on the premise(first sentence) and the counterfactual context(second sentence) of the story.",
        "input": "Premise: Kay was stressed out. \n Initial Context: She'd told her friend Andrea she would write the intro to her new book. \n Original Ending: She wrote many drafts, but none of them were good. Finally, she scribbled down a small paragraph. Andrea felt like Kay hadn't put any effort into it. \n Counterfactual Context: She told her friend Andrea that she would go cover her shift for her new job.",
        "output": "She had to finish her paper before the shift began. Eventually she just scribbled down a small paragraph. Andrea was happy Kay covered for her but Kay failed her paper ",
        "category": "Story Composition 897.json"
    },
    {
        "instruction": "Given a premise, an initial context, an original ending, and a new ending, the task is to generate the counterfactual context that is aligned with the new ending. Each instance consists of a five-sentence story. The premise is the first sentence of a story, and the second sentence, which is the initial context, provides more information about the story's context. The original ending is the last three sentences of the story. Also, you are given a new ending that can provide the new story with the same premise. You should write a counterfactual context to explain the small differences between the original and new endings. More specifically, a story context contains the general plot of the story. And a counterfactual context is a slight modification to the initial context. To sum up, you should write the second sentence of a story based on the premise(first sentence) and the new ending(last three sentences) of the story.",
        "input": "Premise: John arrived home from work. \n Initial Context: He looked through the fridge, but he had nothing to eat. \n Original Ending: John then looked through the freezer to see what to cook. He decided he did not want to cook. John ended up going out to get wings! \n New ending: John then looked through the freezer to see what to cook for dinner. He decided he did not want to cook. John ended up going out to get wings! ",
        "output": "He grabbed something to eat out of the fridge.",
        "category": "Story Composition 898.json"
    },
    {
        "instruction": "In this task, you are given a sentence in the Bulgarian language. Here, your job is to convert bulgarian sentence into the english language.",
        "input": "\u041f\u0440\u0438\u0435\u043c\u0430\u043d\u0435\u0442\u043e \u043d\u0430 \u0430\u043a\u0442 \u043e\u0442 \u0435\u0432\u0440\u043e\u043f\u0435\u0439\u0441\u043a\u043e\u0442\u043e \u0437\u0430\u043a\u043e\u043d\u043e\u0434\u0430\u0442\u0435\u043b\u0441\u0442\u0432\u043e \u0438\u043d\u0438\u0446\u0438\u0438\u0440\u0430 \u043f\u0440\u043e\u0446\u0435\u0441\u0430 \u043f\u043e \u0442\u0440\u0430\u043d\u0441\u043f\u043e\u043d\u0438\u0440\u0430\u043d\u0435 \u0438 \u043f\u0440\u0438\u043b\u0430\u0433\u0430\u043d\u0435 \u043d\u0430 \u0434\u0438\u0440\u0435\u043a\u0442\u0438\u0432\u0430\u0442\u0430 \u0432\u044a\u0432 \u0432\u0441\u044f\u043a\u0430 \u0434\u044a\u0440\u0436\u0430\u0432\u0430-\u0447\u043b\u0435\u043d\u043a\u0430.",
        "output": "in writing. - (SK) The adoption of a piece of European legislation initiates the process of transposing and applying the directive in each Member State.",
        "category": "Translation 899.json"
    },
    {
        "instruction": "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.",
        "input": "9, 17, ['m', '527', '2387', '9333', '335', '899', 'A', 'n', 's', '9841', '8061', 't', 'j', 'r', 'r', 'f', 'Y', '1679', '9901', '9115', '9963', '3637']",
        "output": "s, 9841, 8061, t, j, r, r, f, Y",
        "category": "Program Execution 90.json"
    },
    {
        "instruction": "In this task, you are given a sentence in the english language. Here, your job is to convert english sentence into the bulgarian language.",
        "input": "Now let me answer your question: why the adoption of the Action Plan on Urban Mobility has been delayed.",
        "output": "\u0421\u0435\u0433\u0430 \u043c\u0438 \u043f\u043e\u0437\u0432\u043e\u043b\u0435\u0442\u0435 \u0434\u0430 \u043e\u0442\u0433\u043e\u0432\u043e\u0440\u044f \u043d\u0430 \u0412\u0430\u0448\u0438\u044f \u0432\u044a\u043f\u0440\u043e\u0441: \u0437\u0430\u0449\u043e \u041f\u043b\u0430\u043d\u044a\u0442 \u0437\u0430 \u0434\u0435\u0439\u0441\u0442\u0432\u0438\u0435 \u0437\u0430 \u0433\u0440\u0430\u0434\u0441\u043a\u0430\u0442\u0430 \u043c\u043e\u0431\u0438\u043b\u043d\u043e\u0441\u0442 \u0431\u0435\u0448\u0435 \u0437\u0430\u0431\u0430\u0432\u0435\u043d.",
        "category": "Translation 900.json"
    },
    {
        "instruction": "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\".",
        "input": "Bulgarian: Passamos agora \u00e0 vota\u00e7\u00e3o., English: We shall now proceed to the vote.",
        "output": "yes",
        "category": "Text Matching 901.json"
    },
    {
        "instruction": "In this task, you are given a short passage that may convey stereotype, anti-stereotype, or is unrelated. A stereotype is an over-generalized belief about a particular group of people. An anti-stereotype is an idea that goes against a common stereotype. The passage is unrelated if it does not convey a stereotype or anti-stereotype. You are expected to classify the passage into three classes: stereotype, anti-stereotype, and unrelated.",
        "input": "Passage: The guitarist likes music has a PhD and is very intelligent",
        "output": "Anti-stereotype",
        "category": "Stereotype Detection 907.json"
    },
    {
        "instruction": "In this task, you need to output 'Yes' if the given number is a prime number otherwise output 'No'. A 'prime number' is a a whole number above 1 that can not be made by multiplying other whole numbers.",
        "input": "38461",
        "output": "Yes",
        "category": "Mathematics 91.json"
    },
    {
        "instruction": "In this task, you will be shown a conversation and a question. You need to write an implausible answer to the question. Even though there exist multiple wrong answers, we only need a single wrong answer. \"W\" and \"M\" in the conversations stand for \"woman\" and \"man\".",
        "input": "W: Tomorrow is Mike's birthday. I have just received the invitation to his party. Did Mike invite you, too? M: Yes. I received his invitation this morning. But he didn't tell me what time the party will begin. W: I'll ring him up and ask him about it. How will you go to his party? M: I'll drive to his party after work. Would you like to take my car there? W: I would be glad to. Thank you., Question: When did the man receive the invitation?",
        "output": "This afternoon., Yesterday evening.",
        "category": "Wrong Candidate Generation 911.json"
    },
    {
        "instruction": "In this task, you are given a review of movie. Your task is to classify given movie review into two categories: 1) positive, and 2) negative based on its content.",
        "input": "I hated the first episode of this show ( 'Protesting Hippies' ) so much in 1999 that I shunned the rest. However, when it came on 'The Paramount Comedy Channel' I watched it in full and, to my surprise, found it absolutely hilarious ( Motto: never judge a comedy series in its first week )! Set in 1969, 'Hippies' stars Simon Pegg as 'Ray Purbbs', editor of an 'Oz'-like underground magazine called 'Mouth'. His friends are the feminist Jill, laid-back Alex, and the half-wit Hugo. Back in the late '60's, there was a feeling of incredible optimism amongst the young, that they could change the world through the printing of magazines nobody read. Rather than sneering at the hippies' naivety, 'Hippies' is affectionate towards it. Arthur Mathews' scripts cheekily parody a number of that era's icons - 'Hair', 'Woodstock', 'The Graduate', even the infamous 'Oz' obscenity trial of the early '70's. Excellent performances from the cast; Julian Rhind-Tutt's 'Alex' strangely put me in mind of the Richard O'Sullivan character from 'Man About The House'. Its a shame that there was never a second series, possibly because of people like me. If you missed 'Hippies', give it a try. Once you get past the dire opener, you're in for a treat!",
        "output": "positive",
        "category": "Sentiment Analysis 912.json"
    },
    {
        "instruction": "In this task, you are given a review of a movie and a boolean question whether this review has positive sentiment or negative sentiment. Your task is to generate answer \"yes\" when the tweet has that particular sentiment, otherwise generate answer \"no\".",
        "input": "Review: Geordies...salt of the earth characters...bricklayers...beer...Geordies...happy go lucky...adventures working abroad...salt of the earth characters...warm wonderful people...Tyne Bridge (tear in the eye)...brown ale...salt of the earth characters...cute little Red Indians children in Newcastle United tops...emetic...Geordies...salt of the earth characters...etc etc etc....Please. This is so poor. And you should know better Timothy Spall. They can't have paid you that much.As for Jimmy Nail. Well the kindest thing that can be said is that he is every bit as good an 'actor' as he is a singer and writer. Come on Jimmy, the joke's over. 'Crocodile Shoes' and 'Spender' were very funny, unfortunately I don't think they were supposed to be. With 'Auf Wiedersehen Pet' the opposite applies. Question: is it a negative review?",
        "output": "yes",
        "category": "Sentiment Analysis 913.json"
    },
    {
        "instruction": "In this task you are given a tweet and you must identify whether the tweet contains any offense or any form of (untargeted) profanity. Label the post as NOT if the post does not contain offense or profanity.  Non-offensive posts do not include any form of offense or profanity. label the post as OFFENSIVE if the post contains offensive language or a targeted (veiled or direct) offense.  Twitter user mentions were substituted by @USER and URLs have been substitute by URL.",
        "input": "@USER Another dumbass Democrat. One thing you have to say about this president is he\u2019s not lazy. Another bullshit story as usual",
        "output": "OFFENSIVE",
        "category": "Toxic Language Detection 914.json"
    },
    {
        "instruction": "In this task, you are given a text of article and corresponding title of an article. Your task is to generate label \"yes\" if headline (title) is right for article, otherwise generate \"no\".",
        "input": "Article: a planned texas execution was put on hold wednesday but not because the judge and prosecutor in the convicted killer 's trial were in a sexual relationship at the time , authorities said . Title: us execution on hold but not due to judge-prosecutor affair",
        "output": "yes",
        "category": "Text Matching 917.json"
    },
    {
        "instruction": "In this task, you are given two natural language statements with similar wording. You must choose the statement that makes less sense based on common sense knowledge. A '\n' separates the statements. Use \"first\" or \"second\" to indicate which sentence makes less sense.",
        "input": "Shaun needed to learn more math for his programming job\nShaun needed to learn more dancing for his programming job",
        "output": "second",
        "category": "Commonsense Classification 919.json"
    },
    {
        "instruction": "In this task, you will be given a list of numbers. The goal is to divide all the numbers in the list by a constant such that the sum of the resulting list is 1. The output should be rounded to 3 decimals.",
        "input": "[18.695, 151.593, 143.956, -26.881, 93.796]",
        "output": "[ 0.049  0.398  0.378 -0.071  0.246]",
        "category": "Program Execution 92.json"
    },
    {
        "instruction": "In this task, you're given a story (which contains five sentences only). Your task is to find all the characters which are available in the given story.",
        "input": "Sentence1: Joe took his family to the pet store to pick up dog food. Sentence2: His kids explored the store and found the adoption area. Sentence3: They fell in love with a pretty black and white cat. Sentence4: His kids begged Joe to take it home. Sentence5: Joe gave in and now they have a new member of the family.",
        "output": "Kids, Joe, Family, Cat",
        "category": "Information Extraction 920.json"
    },
    {
        "instruction": "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'.",
        "input": "Context: Susanna really wanted an iPhone. She wanted it mainly for the Touch ID. She thought it would be cool to have. So she went and bought one. \n Sentence: She couldn't have been happier with her purchase. \n Character: Susanna",
        "output": "thrilled, pleased",
        "category": "Sentiment Analysis 921.json"
    },
    {
        "instruction": "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.",
        "input": "Context: Henry was anxiously awaiting the release of an album. His favorite band had promised a new album this weekend. \n Sentence: Still the weekend came and passed with no new music. \n Character: His favorite band",
        "output": "None",
        "category": "Intent Identification 922.json"
    },
    {
        "instruction": "In this task, you are given an impractical statement. You are also given three reasons (associated with \"A\", \"B\", \"C\") explaining why this statement doesn't make sense. You must choose the most corresponding reason explaining why this statement doesn't make sense.",
        "input": "the girl zaps for a car.\n(A) A girl can make a zap decision to purchase a car.\n(B)A girl zaps her brain with car selections to choose from.\n(C)A girl can not zap a car.",
        "output": "C",
        "category": "Explanation 923.json"
    },
    {
        "instruction": "In this task, you're given four sentences of a story written in natural language, and one last sentence (Sentence5). Your job is to classify whether the last sentence completes the rest of the story coherently or not by providing 'Yes' or 'No'.",
        "input": "Sentence1: Shawn woke and rose from the bed at 8:07 am. Sentence2: He reached for his cigarettes but the pack was empty. Sentence3: Shawn then threw on some sweats and headed to the corner store. Sentence4: There, he purchased a pack of Newports. \n Sentence5: Shawn smoked them almost immediately.",
        "output": "Yes",
        "category": "Coherence Classification 926.json"
    },
    {
        "instruction": "In this task, you're given four sentences of a story written in natural language in which one part is missing. Your job is to predict the position and missing part of the story and return in the following format: position, missing part. The missing part is a sentence that completes the story, and the position is the number of the missing sentence in the new story.",
        "input": "Sentence1: Katie couldn't sleep. Sentence2: She poured herself a glass of milk. Sentence3: Then she heated it in the microwave. Sentence4: Katie drank it and went back to bed.",
        "output": "2, She tiptoed downstairs and into the kitchen.",
        "category": "Text Completion 927.json"
    },
    {
        "instruction": "In this task, you're given a short story of five sentences written in natural language. However, the order of the given story is not correct. Your job is to return the correct order for the given five sentences to create a coherent short story with the new order that has the correct flow. Generate your answer using the number of sentences in the correct order, such as '23415'.",
        "input": "Sentence1: Dana's husband Glenn thinks her mother is trying to poison him. Sentence2: During breakfast Glenn stomach starts to cramp. Sentence3: Dana's mother came to visit for a week. Sentence4: However, turns out to just be gas. Sentence5: Glen becomes outraged.",
        "output": "23154",
        "category": "Sentence Ordering 928.json"
    },
    {
        "instruction": "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 _ .",
        "input": "A shocking video has been released showing four tourists they catching a bronzer shark in New Zealand, dragging the thrashing creature in to shore and then pose for photos with the creature. Andreas Rasmussen, Christian Boyum Johansen and Johan Berg are filmed by Emil Fogh, standing just centimetres away from the shark they've captured in an activity that is terrifying but completely legal in New Zealand, to the point it has become a competitive sport. One of the man stands at the water's edge with a fishing line in his hands and the waves lapping at his feet when suddenly he launches forward, dragged by the great weight of the creature who has attached itself to his fishing line.Tourists posted a video of themselves dragging a shark onto shoreThe clip shows them catching the huge shark with a fishing line on a New Zealand beachThey stand just centimetres away from the beast who thrashes angrilyCatching and releasing a shark is a legal sport in New ZealandIt's crucial right techniques are used for safety of fisherman and sharkThe shark should not be touch minimally, but in the video the tourists drag the shark in and pose for photos holding the creature",
        "output": "'The 'catch and release' philosophy is in keeping with _'s dedication to conservation and sustainable fishing,' according to the New Zealand Tourism Guide website.",
        "category": "Question Generation 929.json"
    },
    {
        "instruction": "In this task you will be given a list of numbers and you need to find the mean (average) of that list. The mean of a list can be found by summing every number in the list then dividing the result by the size of that list. The output should be rounded to 3 decimal places.",
        "input": "[145.426, -6.689, 190.674, 234.398]",
        "output": "140.952",
        "category": "Program Execution 93.json"
    },
    {
        "instruction": "In this task, you will be presented with a passage and have to answer a question based on your understanding of the events inferred from the passage. Among the entities, try to find the best entity that is most likely to fill in \"_\" and classify the answers based on options.",
        "input": "A school has allowed a pupil who suffers badly with nerves to take her pet Labrador into a GCSE exam to help keep her calm. Rebecca Rice, 16, had tried everything to calm her nerves but knew the only thing that made her feel comfortable was her 11-year-old dog Holly. After confiding in her teacher Lorette Esteve it was decided she could take Holly into the five-minute recorded French oral test. Rebecca Rice, 16, (right) told her French teacher Lorette Esteve (left) that she had struggled with her nerves ahead of her French GCSE oral exam. Ms Esteve advised her to bring her pet dog Holly (middle) to helpRebecca Rice, 16, was allowed to take her pet dog into five-minute examShe told her teacher she struggles to control her nerves ahead of the GCSETeacher Lorette Esteve advised she bring along 11-year-old dog HollySchool has various tactics help reduce stress including lucky key rings \n Questions:'So _'s mum delivered 11-year-old Labrador Holly to school, and Rebecca spent her five minutes with Holly who sat reassuringly at her side - and it worked.' (A) Labrador (B) Rebecca Rice (C) Holly (D) Lorette Esteve (E) French (F) Esteve",
        "output": "(B)",
        "category": "Question Answering 930.json"
    },
    {
        "instruction": "In this task, you will be presented with a passage, and you need to write an **implausible** answer to to fill in the place of \"_\". Your answer should be incorrect, but should not be out of context. Try using words that are related to the context of the passage, but are not the correct answer.  Even though there exist multiple wrong answers, we only need a single wrong answer.",
        "input": "The surrender of Confederate Gen. Robert E. Lee to Union Lt. Gen. Ulysses S. Grant 150 years ago on Thursday was a milestone event in the end of the Civil War. Thursday's commemoration in Appomattox, Virginia, included a reenactment of Lee's last clash with Grant's troops and of the Confederate surrender in a Virginia farmhouse on April 9, 1865. Ahead of the battle reenactment, the boys of the Confederate 11th Virginia were a seemingly pretty cool bunch as those portraying Union troops gathered several fields away at Appomattox Court House amid the rolling farm country dotted by neat brick buildings and white picket fences.Confederate\u00a0Gen. Robert E. Lee surrendered to Union Lt. Gen. Ulysses S. Grant on April 9, 1865The surrender in Appomattox, Virginia, is considered a milestone event in the ending of the Civil WarRe-enactors gathered in Appomattax for a re-enactment of the\u00a0Battle of Appomattox Courthouse \n Question:_ and Union re-enactors dressed in gear likened to what was worn during the Civil War, 150 years ago.",
        "output": "Robert E. Lee, Union, Ulysses S. Grant, Civil War, Appomattox, Virginia, Lee, Grant, Appomattox Court House, Appomattax, Battle of Appomattox Courthouse",
        "category": "Wrong Candidate Generation 931.json"
    },
    {
        "instruction": "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.",
        "input": "Maura Isles:  Look at these two bottles of the secret sauce\nJane Rizzoli: That one 's darker\nMaura Isles: Yes . Now taste them\nJane Rizzoli: Taste them ? No ! We 're in the crime lab , it 's not very appetizing . Maur ...\nMaura Isles: Just taste it !\nJane Rizzoli: It 's good\nMaura Isles: Mm , hmm , now try this _ one _\nJane Rizzoli: They 're the same\nMaura Isles: If you 're not a super taster , it does\nJane Rizzoli: I think , I 've just been insulted",
        "output": "OTHER",
        "category": "Coreference Resolution 932.json"
    },
    {
        "instruction": "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 consistency, answers should be in all lower cased letters.",
        "input": "Category: NOTABLE NAMES \nClue: On July 20, 1969 at 10:56 P.M. Eastern Daylight Time, he became the first man to set foot on the moon",
        "output": "neil armstrong",
        "category": "Misc. 933.json"
    },
    {
        "instruction": "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.",
        "input": "Category: HERALDIC BEASTS \nClue: This animal is on the Lopez family coat of arms, probably because of the name Lopez comes from the Latin for it",
        "output": "a wolf",
        "category": "Misc. 934.json"
    },
    {
        "instruction": "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.",
        "input": "Category: FROM PAGE TO SCREEN \nClue: David Guterson's book about racism in the Pacific Northwest became this 1999 film that stars a brooding Ethan hawke",
        "output": "snow falling on cedars",
        "category": "Misc. 936.json"
    },
    {
        "instruction": "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.",
        "input": "[-34.569  26.223  78.637 -22.798  17.147  97.921 -20.479  44.134 -62.783\n -85.104]",
        "output": "97.921",
        "category": "Program Execution 94.json"
    },
    {
        "instruction": "In this task, you are given a sentence in the Swedish language and your task is to convert it into the English language. In translation, keep numbers as it is and make it sentence case (capitalize only the first word of each sentence and noun).",
        "input": "Det finns andra fr\u00e5gor som borde vara givande att granska framf\u00f6r allt f\u00f6re en s\u00e5 stor utvidgning av unionen med s\u00e5 m\u00e5nga nya l\u00e4nder.",
        "output": "There are other issues that should fruitfully be looked at, especially before such a large widening of the Union to so many new countries.",
        "category": "Translation 940.json"
    },
    {
        "instruction": "In this task, you are given a sentence in the English language and your task is to convert it into the Swedish language. In translation, keep numbers as it is and make it sentence case (capitalize only the first word of each sentence and noun).",
        "input": "This hope is contained in our motion for a resolution. We hope for a fair and balanced agreement based on respect for sovereignties and the right to live securely within safe and recognised borders.",
        "output": "Det \u00e4r vad v\u00e5r resolution uttrycker: en f\u00f6rhoppning om ett rimligt och r\u00e4ttvist avtal, grundat p\u00e5 respekt f\u00f6r de suver\u00e4na staterna och r\u00e4tten att leva i s\u00e4kerhet inom s\u00e4kra och erk\u00e4nda gr\u00e4nser.",
        "category": "Translation 941.json"
    },
    {
        "instruction": "In this task, you are given a sentence in the Swedish language and a corresponding English translation of the Swedish sentence. Your task is to generate a label \"Yes\" if the translation is correct, otherwise generate label \"No\".",
        "input": "Swedish: I ett n\u00f6tskal: programverksamhet bedrevs utan att det fanns tillr\u00e4ckliga personalresurser tillg\u00e4ngliga. \n English: What concerns me most in Mr Miranda's report is the postponement of the discharge decision in respect of the Economic and Social Committee.",
        "output": "No",
        "category": "Text Matching 942.json"
    },
    {
        "instruction": "In this task, you are given a sentence which is either in the Swedish language or English language. You task is to identify the language of input sentence. Input sentence can be in Swedish or English language only and also it cannot have two languages at a time.",
        "input": "The CEO of the authority would be somebody who typically would be known, who might appear regularly on television talking about issues relating to food, particularly in relation to the good news stories surrounding food in relation to nutrition, diet and such issues, so that if another food crisis comes along consumers will be aware of the existence of the authority.",
        "output": "English",
        "category": "Text Matching 943.json"
    },
    {
        "instruction": "In this task you will be given a list of numbers and you need to subtract every value in the list with the index it is at. The index of an elements shows its numerical order in the list(for example, in the list [7,10,4,5], the index of 7 is 1 and the index of 4 is 3)  You should start the index at 1, so the first element in the list will be subtracted by one. For every element in the list you need to find \"element - index\" where the index of the beginning element is 1 and increments by 1 for each element. Put your result list in brackets.",
        "input": "[-13, 5, 7, 13, 16, 19, -14, 9, 1]",
        "output": "[-14, 3, 4, 9, 11, 13, -21, 1, -8]",
        "category": "Program Execution 95.json"
    },
    {
        "instruction": "In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: threat and non-threat. Threat is a statement that someone will be hurt or harmed, especially if the person does not do something in particular.",
        "input": "Comment: You are a bad egg in here! Do you ever respond with intelligence, wit, or possibly, a helpful suggestion? You take up space that otherwise, might have value.",
        "output": "Non-threat",
        "category": "Toxic Language Detection 950.json"
    },
    {
        "instruction": "In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: sexual-explicit and non-sexual-explicit. A comment is considered sexual-explicit if it explicitly portrays sexual matters.",
        "input": "Comment: You are once again talking out of your behind and wrong.",
        "output": "Sexual-explicit",
        "category": "Toxic Language Detection 951.json"
    },
    {
        "instruction": "In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: identity-attack and non-identity-attack. Identity attack refers to anything rude or disrespectful about someone's identity, including appearance, race, gender, and sexual orientation.",
        "input": "Comment: This story is about a left wing black man who \"expresses disdain for President Donald Trump and white people generally.\" I'm not sure about the purpose of your rant.",
        "output": "Identity-attack",
        "category": "Toxic Language Detection 953.json"
    },
    {
        "instruction": "In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: obscene and non-obscene. A comment is obscene if it is considered offensive to the public sense of decency, for example because it too obviously relates to sex or contains language regarded as taboo in polite usage.",
        "input": "Comment: \"We should also acknowledge that scientism itself has a grim history when conscripted by modern governments. As the totalitarian regimes of the 20th century showed, this can lead to a ruthless utilitarianism that strips men and women of their humanity. \"\n\nThis is a bit of conclusion hopping. So the Governor General derided the religious as ignorant. Alright. Maybe it was smart move and maybe it wasn't. But this nonsense is dumber than anything she said.",
        "output": "Non-obscene",
        "category": "Toxic Language Detection 954.json"
    },
    {
        "instruction": "In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: toxic and non-toxic. Toxicity is defiend as anything that is rude, disrespectful, or unreasonable that would make someone want to leave a converation.",
        "input": "Comment: Right. More poor, white trash are on EBT/ SNAP",
        "output": "Toxic",
        "category": "Toxic Language Detection 955.json"
    },
    {
        "instruction": "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.",
        "input": "Comment: The elephant in the room is the Denver Post. Keeping the useful idiots, idiots.",
        "output": "Insult",
        "category": "Toxic Language Detection 956.json"
    },
    {
        "instruction": "In this task, you will be presented with a text, a pronoun from the text, and two candidate names. You should determine what the pronoun refers to and classify the answers into A, B, or Neither. A and B here are referring to option A and option B. Position of the pronoun in the text is showed within two \"_\"s.",
        "input": "She was also more opened about Olivia's decision to reveal her plan to Ian after only knowing him for less than a day. Kat Ward of Entertainment Weekly was more critical towards Olivia and Ian's friendship as she wrote ``I know that circumstances can make for strange friends, but Liv and Poor Ian get close very fast.'' _She_ continued talking about Olivia's belief in Fitz's ability to save her writing ``Personally I think that Olivia's particular faith in her importance is more than a little overblown. <sep>, Pronoun: She <sep>, A: Liv <sep>, B: Olivia",
        "output": "Neither",
        "category": "Coreference Resolution 957.json"
    },
    {
        "instruction": "In this task, you will be presented with a text and a pronoun. You should write the name that the pronoun refers to. Position of the pronoun in the text is showed within two \"_\"s.",
        "input": "O'Sullivan partied all night, provoking that year's winner Charmaine Kenny to say she felt like ``a bit of a party popper'' for having had one hour of sleep and ``a bit of a lightweight beside her''. O'Sullivan, instead of going to bed, then embarked on a 3 kilometre walk the following morning. Victoria Mary Clarke later wrote in the Sunday Independent of how O'Sullivan ``glided glamorously through the hotel'', commenting that ``when I am _her_ age, I would not object to being like her''. <sep>, Pronoun: her",
        "output": "O'Sullivan",
        "category": "Coreference Resolution 958.json"
    },
    {
        "instruction": "In this task, you will be presented with a text and a pronoun. You should write an implausible answer to the question of what is the pronoun's reference. Even though there exist multiple wrong answers, we only need a single wrong answer. Position of the pronoun in the text is showed within two \"_\"s.",
        "input": "In his first MLB at bat (in his fourth game played), on September 20, 1964, at Fenway Park, Bethea doubled off Ed Connolly of the Boston Red Sox, driving home Bob Allison from first base for his first run batted in in the Majors. It sparked the Twins to a 12--4 victory. In _his_ brief big-league trial, however, Bethea collected only five total hits and two RBI in ten games played and 30 at bats. <sep>, Pronoun: his",
        "output": "Twins",
        "category": "Wrong Candidate Generation 959.json"
    },
    {
        "instruction": "In this task you will be given a list of numbers and you should remove all duplicates in the list. If every number is repeated in the list an empty list should be returned. Your list should be numbers inside brackets, just like the given list.",
        "input": "[1, 7, 1, 2, 3, 3, 5, 0, 1, 2]",
        "output": "[7, 5, 0]",
        "category": "Program Execution 96.json"
    },
    {
        "instruction": "In this task, you are given a post in English from online platforms. You are expected to identify whether the post is hateful against immigrants and women. A hateful post expresses hate or encourages violence towards a person or a group. If a post is hateful but not towards immigrants and women, it should be labeled as non-hateful. Answer \"hateful\" or \"Non-hateful\". Note that the URLs in the text have been replaced with [Link].",
        "input": "Post: When you put it in her butt without tellin her and her head spins all the way around to cuss you out [Link]",
        "output": "Non-hateful",
        "category": "Toxic Language Detection 961.json"
    },
    {
        "instruction": "In this task, you are given a post in Spanish from online platforms. You are expected to identify whether the post is hateful against immigrants and women. A hateful post expresses hate or encourages violence towards a person or a group. If a post is hateful but not towards immigrants and women, it should be labeled as non-hateful. Answer \"hateful\" or \"Non-hateful\". Note that the URLs in the text have been replaced with [Link].",
        "input": "Post: Estamos en un Estado de igualdad, no? Para cuando la escena de un hombre que diga, 'busco a una guarra para poder fornicar como un loco despechado hasta nuevo a\u00f1o'? No es esto una descarada y funesta forma de incitar el incorrectismo coyuntural y los falsos modales? [Link]",
        "output": "Non-hateful",
        "category": "Toxic Language Detection 962.json"
    },
    {
        "instruction": "In this task, you will be presented with a passage and have to answer a question based on your understanding of the events inferred from the passage. Try to find the best answer that is most likely to fill in \"_\". Note that the URLs in the text have been replaced with [Link].",
        "input": "They call it a sombrero in Spain \u2013 flicking the ball over a player's head and retrieving it the other side of him. When Neymar did it in the last minutes of the Spanish Cup final against Athletic Bilbao he was accused of excessive showboating. His answer: 'You ain't seen nothing yet.' In Brazil's first game of the Copa America he flicked the ball over Peruvian midfielder Luis Adv\u00edncula's head and then did it again \u2013 a double sombrero. No player has more tricks up his sleeve than Neymar and the magic isn't just to rub opponents noses in defeat as he was accused of doing in the Spanish Cup Final. He does it to win. He is not interested in points for an artistic impression - he wants a goal.Neymar's pulled off an outrageous sombrero flick against PeruHe pulled off the same trick playing Athletic Bilbao and was criticisedThe 22-year-old is next in line to take Lionel Messi's crownNeymar starred for Brazil as they won their Copa America openerA future Ballon d'Or is all but certain if he carries on progressingCLICK HERE for all the latest Barcelona news \n Question:At 23, _ will soon pass Zico's haul of 48 and he will have Ronaldo on 62 goals and Romario on 55 in his sights.",
        "output": "Neymar",
        "category": "Question Answering 967.json"
    },
    {
        "instruction": "In this task you will be given two lists of numbers and you need to calculate the intersection between these two lists. The intersection between two lists is another list where every element is common between the two original lists. If there are no elements in the intersection, answer with an empty list. Your list of numbers must be inside brackets. Sort the numbers in your answer in an ascending order, that is, no matter what the order of the numbers in the lists is, you should put them in your answer in an ascending order.",
        "input": "[1, 8, 8, 7, 9, 1, 5, 3, 4, 9] , [2, 5, 9, 6, 8, 10, 6, 8, 8, 6]",
        "output": "[5, 8, 9]",
        "category": "Program Execution 97.json"
    },
    {
        "instruction": "In this task, you will be presented with a question and you have to answer the question based on your knowledge. Your answers should be as short as possible.",
        "input": "What are the tracks in the hottest 100 for the artist that signed to Infectious Music in the UK/Europe ; and Votiv in North America ?",
        "output": "18",
        "category": "Question Answering 972.json"
    },
    {
        "instruction": "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$: Possessive wh-pronoun, WRB: Wh-adverb",
        "input": "How many towns are on the route to see Germanys ninth largest island ?",
        "output": "WRB JJ NNS VBP IN DT NN TO VB NNP RB JJS NN .",
        "category": "Pos Tagging 973.json"
    },
    {
        "instruction": "In this task, you will be presented with a question, a word, and a POS tag. You have to determine whether the part-of-speech tag of the given word in the question is equal to the given POS tag or not. Give your answer with True or False. Here is the Alphabetical list of part-of-speech tags used in this task: CC: Coordinating conjunction, CD: Cardinal number, DT: Determiner, EX: Existential there, FW: Foreign word, IN: Preposition or subordinating conjunction, JJ: Adjective, JJR: Adjective, comparative, JJS: Adjective, superlative, LS: List item marker, MD: Modal, NN: Noun, singular or mass, NNS: Noun, plural, NNP: Proper noun, singular, NNPS: Proper noun, plural, PDT: Predeterminer, POS: Possessive ending, PRP: Personal pronoun, PRP$: 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$: Possessive wh-pronoun, WRB: Wh-adverb",
        "input": "How many Olympics did the winner of the 800m compete in ? \n, Word: 800m \n, POS tag: NNPS",
        "output": "False",
        "category": "Pos Tagging 974.json"
    },
    {
        "instruction": "In this task, you will be presented with a question about part-of-speech tag of a word in the question. You should write an implausible POS tag to the question. Even though there exist multiple wrong answers, we only need a single wrong answer.  Here is the Alphabetical list of part-of-speech tags used in this task: CC: Coordinating conjunction, CD: Cardinal number, DT: Determiner, EX: Existential there, FW: Foreign word, IN: Preposition or subordinating conjunction, JJ: Adjective, JJR: Adjective, comparative, JJS: Adjective, superlative, LS: List item marker, MD: Modal, NN: Noun, singular or mass, NNS: Noun, plural, NNP: Proper noun, singular, NNPS: Proper noun, plural, PDT: Predeterminer, POS: Possessive ending, PRP: Personal pronoun, PRP$: Possessive pronoun, RB: Adverb, RBR: Adverb, comparative, RBS: Adverb, superlative, RP: Particle, SYM: Symbol, TO: to, UH: Interjection, VB: Verb, base form, VBD: Verb, past tense, VBG: Verb, gerund or present participle, VBN: Verb, past participle, VBP: Verb, non-3rd person singular present, VBZ: Verb, 3rd person singular present, WDT: Wh-determiner, WP: Wh-pronoun, WP$: Possessive wh-pronoun, WRB: Wh-adverb",
        "input": "What is the part-of-speech tag of the word \"Games\" in the following question: Why did people decline to choose the bronze medalist in women 's 1.5 km speed skating at the Olympic Games of 1968 for the Olympic Games of 1964 ?",
        "output": "IN",
        "category": "Pos Tagging 975.json"
    },
    {
        "instruction": "This task is about creating an unanswerable question based on a given passage. Construct a question that looks relevant to the given context but is unanswerable. Following are a few suggestions about how to create unanswerable questions:\n(i) create questions which require satisfying a constraint that is not mentioned in the passage\n(ii) create questions which require information beyond what is provided in the passage in order to answer\n(iii) replace an existing entity, number, date mentioned in the passage with other entity, number, date and use it in the question\n(iv) create a question which is answerable from the passage and then replace one or two words by their antonyms or insert/remove negation words to make it unanswerable.",
        "input": "Passage: The IPCC Panel is composed of representatives appointed by governments and organizations. Participation of delegates with appropriate expertise is encouraged. Plenary sessions of the IPCC and IPCC Working groups are held at the level of government representatives. Non Governmental and Intergovernmental Organizations may be allowed to attend as observers. Sessions of the IPCC Bureau, workshops, expert and lead authors meetings are by invitation only. Attendance at the 2003 meeting included 350 government officials and climate change experts. After the opening ceremonies, closed plenary sessions were held. The meeting report states there were 322 persons in attendance at Sessions with about seven-eighths of participants being from governmental organizations.",
        "output": "Which non-governmental groups are participants of the plenary sessions?, Which IPCC sessions are open to everyone?, What year did more than 375 officials attend the IPCC Bureau session?, Which sessions had a majority attendance from non-governmental organizations?, What session did the IPCC panel attend before the opening ceremonies?",
        "category": "Question Generation 976.json"
    },
    {
        "instruction": "In this task, you are given a passage and a question regarding that passage. You must determine whether or not the question is answerable from the given passage. If a question is answerable, output should be 'True', otherwise 'False'. You must not consider any other information that is not provided in the passage while labelling True or False.",
        "input": "Passage: Many Han Chinese and Khitan defected to the Mongols to fight against the Jin. Two Han Chinese leaders, Shi Tianze, Liu Heima (\u5289\u9ed1\u99ac, Liu Ni), and the Khitan Xiao Zhala (\u856d\u672d\u524c) defected and commanded the 3 Tumens in the Mongol army. Liu Heima and Shi Tianze served Og\u00f6dei Khan. Liu Heima and Shi Tianxiang led armies against Western Xia for the Mongols. There were 4 Han Tumens and 3 Khitan Tumens, with each Tumen consisting of 10,000 troops. The three Khitan Generals Shimobeidier (\u77f3\u62b9\u5b5b\u8fed\u5152), Tabuyir (\u5854\u4e0d\u5df2\u5152) and Xiaozhacizhizizhongxi (\u856d\u672d\u523a\u4e4b\u5b50\u91cd\u559c) commanded the three Khitan Tumens and the four Han Generals Zhang Rou, Yan Shi, Shi Tianze, and Liu Heima commanded the four Han tumens under Og\u00f6dei Khan. Question: What Khitan leader defected to the Mongols?",
        "output": "True",
        "category": "Answerability Classification 977.json"
    },
    {
        "instruction": "In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to list all elements of A from the ith element to the jth element in the reverse order. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.",
        "input": "3, 4, ['8399', 'c', 'm', '1495', '4605', 'H', '3613', 'T', '7223', '9381', 'Q', '489', '625']",
        "output": "1495, m",
        "category": "Program Execution 98.json"
    },
    {
        "instruction": "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...'. ",
        "input": "Mitch, what happened to you? You're not talking like yourself.",
        "output": "Look, I'm not feeling like myself. Feeling all sweaty and dehydrated. I think it was the olive oil I drank. Mixed with the saltwater.",
        "category": "Dialogue Generation 988.json"
    },
    {
        "instruction": "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...'. ",
        "input": "Prompt: As a gesture of diplomacy, please take a Blu-Ray DVD copy of my film, Life is Beautiful. \n Response: I love Noises Off. It's like a long episode of Fraiser.",
        "output": "no",
        "category": "Dialogue Generation 989.json"
    },
    {
        "instruction": "\"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...\"). Given a prompt and two responses, identify which response is the type of \"yes, and\". Indicate your answer by 'Response 1' if the first response is correct, otherwise 'Response 2'.  Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange.",
        "input": "Prompt: I showed up, like, 45 years ago to get this job done and we've been haggling for years. \n Response 1: How did you end up in this painting? \n Response 2: Oh, come on. People like it.",
        "output": "Response 1",
        "category": "Dialogue Act Recognition 990.json"
    },
    {
        "instruction": "In this task, you are given sentences from movie reviews. The task is to classify a sentence as \"POS\" if the sentiment of the sentence is positive or as \"NEG\" if the sentiment of the sentence is negative",
        "input": "A thoroughly awful movie -- dumb , narratively chaotic , visually sloppy ... a weird amalgam of ` The Thing ' and a geriatric ` Scream . '",
        "output": "NEG",
        "category": "Sentiment Analysis 991.json"
    },
    {
        "instruction": "In this task you will be given a string of characters. You should remove all vowels from the given string. Vowels are: i,e,a,u,o. The character 'y' or 'Y' does not count as a vowel.",
        "input": "auMy",
        "output": "My",
        "category": "Program Execution 993.json"
    },
    {
        "instruction": "In this task you will be given a list of integers. You should remove any integer that is not prime. A prime integer is an integer that is only divisible by '1' and itself. The output should be the list of prime numbers in the input list. If there are no primes in the input list an empty list (\"[]\") should be returned.",
        "input": "[97, 689, 760, 239, 464, 541, 159, 673, 173, 53, 850, 18]",
        "output": "[97, 239, 541, 673, 173, 53]",
        "category": "Program Execution 994.json"
    },
    {
        "instruction": "In this task you will be given a list of numbers. You should remove any number that is not an integer (whole number). If every number is not an whole number then an empty list (\"[]\") should be returned. Otherwise, answer with the list of whole numbers separated by comma inside brackets.",
        "input": "[51, -77, 19, 12.691, 44, -58, -23.426, -16.138]",
        "output": "[51, -77, 19, 44, -58]",
        "category": "Program Execution 995.json"
    },
    {
        "instruction": "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.",
        "input": "[60, -26, -36, 27]",
        "output": "[15.0, -6.5, -9.0, 110]",
        "category": "Program Execution 996.json"
    },
    {
        "instruction": "In this task, you will be given a list of integers. You should remove all of the odd integers from the list(consider 0 an even number). If every integer in the input list is odd then an empty list (\"[]\") should be returned. Otherwise, answer with the list of even numbers separated by comma inside brackets.",
        "input": "[79, -3, 58, 98, 99, 0, 52]",
        "output": "[58, 98, 0, 52]",
        "category": "Program Execution 997.json"
    },
    {
        "instruction": "In this task you will be given a list of integers. You should remove all of the integers that are divisible by 3 from the list. If every integer in the input list is divisible by 3 then an empty list should be returned. Zero is divisible by 3.",
        "input": "[-65, 95, -69, 80, 52]",
        "output": "[-65, 95, 80, 52]",
        "category": "Program Execution 998.json"
    },
    {
        "instruction": "In this task you will be given a list of lists, of numbers. For every inner list, you should multiply every number in that list and put the results in your answer. The output should be a list of numbers with the same length as the number of the lists in the input list.",
        "input": "[[-48, -12, -29, -39, -11], [-17, -26, 16], [13, 5, 43, 48, 28], [26, 15, -35, -14, -26], [-2, -17, 35, 13, 46], [30, -15, -41], [-30, 3, 40, -6], [28, -40]]",
        "output": "[-7166016, 7072, 3756480, -4968600, 711620, 18450, 21600, -1120]",
        "category": "Program Execution 999.json"
    }
]