{"url":"/dataset/cc-dbp","name":"CC-DBP","full_name":null,"description_markdown":"**CC-DBP** is a dataset for knowledge base population research using Common Crawl and DBpedia.\r\n\r\nSource: [https://github.com/IBM/cc-dbp](https://github.com/IBM/cc-dbp)","description_withheld":null,"homepage":"https://github.com/IBM/cc-dbp","introduced_date":"2018-06-03","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-dataset-for-web-scale-knowledge-base","title":"A Dataset for Web-Scale Knowledge Base Population","first_author":"Michael Glass","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[],"variants":["CC-DBP"],"data_loaders":[{"repo":"https://github.com/IBM/cc-dbp","url":"https://github.com/IBM/cc-dbp","frameworks":[]}],"num_papers_in_archive":4,"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."}