{"url":"/dataset/dbp1m-fr-en","name":"DBP1M FR-EN","full_name":null,"description_markdown":"A large-scale cross-lingual dataset for entity alignment","description_withheld":null,"homepage":"https://github.com/ZJU-DAILY/LargeEA","introduced_date":"2021-08-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/largeea-aligning-entities-for-large-scale","title":"LargeEA: Aligning Entities for Large-scale Knowledge Graphs","first_author":null,"url":null},"license":null,"modalities":[],"tasks":[{"name":"Entity Alignment","url":"/task/entity-alignment","datasets_with_task":"/datasets/task/entity-alignment"}],"languages":[],"variants":["DBP1M FR-EN"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/entity-alignment-on-dbp1m-fr-en","task":"Entity Alignment","dataset_variant":"DBP1M FR-EN","rows":2,"metrics":["Hit@1"],"first_row_in_archive_order":{"model":"LightEA","paper":"/paper/lightea-a-scalable-robust-and-interpretable","metrics":{"Hit@1":"0.285"},"code_links":[{"title":"THU-KEG/Entity_Alignment_Papers","url":"https://github.com/THU-KEG/Entity_Alignment_Papers"},{"title":"maoxinn/lightea","url":"https://github.com/maoxinn/lightea"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/lightea-a-scalable-robust-and-interpretable","title":"LightEA: A Scalable, Robust, and Interpretable Entity Alignment Framework via Three-view Label Propagation","date":"2022-10-19","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/clusterea-scalable-entity-alignment-with","title":"ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similarities","date":"2022-05-20","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":0,"samples_unverified":15,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":16,"samples_ran":0,"samples_unverified":16,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":2,"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."}