{"url":"/dataset/biographical","name":"Biographical","full_name":"Biographical: A Semi-Supervised Relation Extraction Dataset","description_markdown":"Biographical is a semi-supervised dataset for RE. The dataset, which is aimed towards digital humanities (DH) and historical research, is automatically compiled by aligning sentences from Wikipedia articles with matching structured data from sources including Pantheon and Wikidata.","description_withheld":null,"homepage":"https://plumaj.github.io/biographical/","introduced_date":"2022-05-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/biographical-a-semi-supervised-relation","title":"Biographical: A Semi-Supervised Relation Extraction Dataset","first_author":"Alistair Plum","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Graphs","url":"/datasets/modality/graphs"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"Relation Extraction","url":"/task/relation-extraction","datasets_with_task":"/datasets/task/relation-extraction"},{"name":"Knowledge Graphs","url":"/task/knowledge-graphs","datasets_with_task":"/datasets/task/knowledge-graphs"},{"name":"NER","url":"/task/cg","datasets_with_task":"/datasets/task/cg"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Biographical"],"data_loaders":[],"num_papers_in_archive":2,"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."}