{"url":"/dataset/wikiwiki","name":"WikiWiki","full_name":null,"description_markdown":"**WikiWiki** is a dataset for understanding entities and their place in a taxonomy of knowledge—their types. It consists of entities and passages from 10M Wikipedia articles linked to the Wikidata knowledge graph with 41K types.","description_withheld":null,"homepage":"https://github.com/amazon-research/wikiwiki-dataset/","introduced_date":"2022-04-28","introduced_date_note":null,"introduced_by":{"paper":"/paper/instilling-type-knowledge-in-language-models","title":"Instilling Type Knowledge in Language Models via Multi-Task QA","first_author":"Shuyang Li","url":null},"license":{"name":"CC BY-NC 4.0","url":"https://github.com/amazon-research/wikiwiki-dataset/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Knowledge Graphs","url":"/task/knowledge-graphs","datasets_with_task":"/datasets/task/knowledge-graphs"}],"languages":[],"variants":["WikiWiki"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}