{"url":"/dataset/dbpedia-nif","name":"DBpedia NIF","full_name":null,"description_markdown":"The dataset provides the content of all articles for 128 Wikipedia languages. The dataset has been further enriched with about 25% more links and selected partitions published as Linked Data. \r\n\r\nSource: [DBpedia NIF: Open, Large-Scale and Multilingual Knowledge Extraction Corpus](/paper/dbpedia-nif-open-large-scale-and-multilingual)","description_withheld":null,"homepage":"https://wiki.dbpedia.org/nif-abstract-datasets","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/dbpedia-nif-open-large-scale-and-multilingual","title":"DBpedia NIF: Open, Large-Scale and Multilingual Knowledge Extraction Corpus","first_author":"Milan Dojchinovski","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[],"variants":["DBpedia NIF"],"data_loaders":[],"num_papers_in_archive":1,"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."}