{"url":"/dataset/tempqa-wd","name":"TempQA-WD","full_name":null,"description_markdown":"**TempQA-WD** is a benchmark dataset for temporal reasoning designed to encourage research in extending the present approaches to target a more challenging set of complex reasoning tasks. Specifically, the benchmark is a temporal question answering dataset with the following advantages: (a) it is based on Wikidata, which is the most frequently curated, openly available knowledge base, (b) it includes intermediate sparql queries to facilitate the evaluation of semantic parsing based approaches for KBQA, and (c) it generalizes to multiple knowledge bases: Freebase and Wikidata.","description_withheld":null,"homepage":"https://github.com/IBM/tempqa-wd","introduced_date":"2022-01-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-benchmark-for-generalizable-and","title":"A Benchmark for Generalizable and Interpretable Temporal Question Answering over Knowledge Bases","first_author":"Sumit Neelam","url":null},"license":{"name":"Creative Commons Zero v1.0 Universal","url":"https://github.com/IBM/tempqa-wd/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"}],"languages":[],"variants":["TempQA-WD"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-tempqa-wd","task":"Question Answering","dataset_variant":"TempQA-WD","rows":2,"metrics":["F1"],"first_row_in_archive_order":{"model":"BestOfBoth","paper":null,"metrics":{"F1":"41.6"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/sygma-system-for-generalizable-modular","title":"SYGMA: System for Generalizable Modular Question Answering OverKnowledge Bases","date":"2021-09-28","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"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."}