HIPE-2026 is a CLEF 2026 Evaluation Lab on the qualification of person\u2013place relations in multilingual historical documents (Who was where, when?). This release contains the complete v1.0 dataset used during the official evaluation campaign.
\n\nThe HIPE-2026 dataset covers two evaluation domains across two test sets:
\nat and isAt relations.at only.| Split | Domain | Languages | File(s) |\n|---|---|---|---|\n| Train | Newspapers | DE, EN, FR | data/newspapers/v1.0/HIPE-2026-v1.0-impresso-train-*.jsonl |\n| Test | Newspapers | DE, EN, FR | data/newspapers/v1.0/HIPE-2026-v1.0-impresso-test-*.jsonl |\n| Test (masked) | Newspapers | DE, EN, FR | data/newspapers/v1.0/HIPE-2026-v1.0-impresso-test_masked-*.jsonl |\n| Test | Literary works | FR | data/litworks/v1.0/HIPE-2026-v1.0-surprise-test-fr.jsonl |\n| Test (masked) | Literary works | FR | data/litworks/v1.0/HIPE-2026-v1.0-surprise-test_masked-fr.jsonl |
For detailed information on tasks, datasets, and evaluation protocol, refer to the CLEF HIPE-2026 Shared Task Participation Guidelines.
\nThe full campaign evaluation \u2014 including reference data, participant submissions, and the evaluation orchestrator \u2014 is available at:\n\ud83d\udc49 https://github.com/hipe-eval/hipe-2026-eval
\nData is distributed as UTF-8 JSON Lines (.jsonl). Each line is one document with OCR text, document metadata, and sampled person\u2013location pairs. Prediction targets are:
at \u2014 evidence that a person was at a location at any time before publication (TRUE, FALSE, PROBABLE, null)isAt \u2014 evidence of presence within ~one month before publication (TRUE, FALSE, null)The full schema is in schemas/hipe-2026-data.schema.json. See the README for format details, validation, and a prediction/evaluation walkthrough.
\n\nJuri Opitz, Corina Racl\u00e9, Andrianos Michail, Matteo Romanello, Emanuela Boros, Simon Gabay, Maud Ehrmann, and Simon Clematide. 2026. Extended Overview of HIPE-2026: Evaluating Accurate and Efficient Person\u2013Place Relation Extraction from Multilingual Historical Texts. In CLEF 2026 Working Notes, CEUR Workshop Proceedings. https://doi.org/10.5281/zenodo.20344461
\n
Released under CC BY-NC-SA 4.0.
\nHIPE-2026 is organised within the Impresso project, funded by the Swiss National Science Foundation (grant CRSII5_213585) and the Luxembourg National Research Fund (grant 17498891).
", "publication_date": "2026-06-09", "publisher": "Zenodo", "related_identifiers": [ { "identifier": "https://github.com/hipe-eval/HIPE-2026-data/tree/v1.0", "relation_type": { "id": "issupplementto", "title": { "de": "Erg\u00e4nzt", "en": "Is supplement to" } }, "resource_type": { "id": "software", "title": { "de": "Software", "en": "Software" } }, "scheme": "url" } ], "resource_type": { "id": "dataset", "title": { "de": "Datensatz", "en": "Dataset" } }, "rights": [ { "description": { "en": "The Creative Commons Attribution license allows re-distribution and re-use of a licensed work on the condition that the creator is appropriately credited." }, "icon": "cc-by-icon", "id": "cc-by-4.0", "props": { "scheme": "spdx", "url": "https://creativecommons.org/licenses/by/4.0/legalcode" }, "title": { "en": "Creative Commons Attribution 4.0 International" } } ], "title": "HIPE-2026 Shared Task Person-Place Relation Dataset", "version": "v1.0" }, "parent": { "access": { "owned_by": { "user": "44474" }, "settings": { "accept_conditions_text": null, "allow_guest_requests": false, "allow_user_requests": false, "secret_link_expiration": 0 } }, "communities": { "default": "e054c200-d2d3-43c8-af38-c9813962ee5c", "entries": [ { "access": { "member_policy": "open", "members_visibility": "public", "record_submission_policy": "open", "review_policy": "open", "visibility": "public" }, "children": { "allow": false }, "created": "2022-02-11T13:17:33.651553+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "id": "e054c200-d2d3-43c8-af38-c9813962ee5c", "links": {}, "metadata": { "curation_policy": "The HIPE-EVAL Zenodo community is for datasets, guidelines and papers related to the HIPE shared tasks.
\r\n", "description": "HIPE is a series of evaluation campaigns on named entity processing on historical documents in multiple languages.", "page": "HIPE is a series of evaluation campaigns on named entity processing on historical documents in multiple languages.
\r\n", "title": "HIPE evaluation campaigns" }, "revision_id": 0, "slug": "hipe-eval", "updated": "2022-02-11T13:18:06.841769+00:00" } ], "ids": [ "e054c200-d2d3-43c8-af38-c9813962ee5c" ] }, "id": "20615689", "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.20615689", "provider": "datacite" } } }, "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.20615690", "provider": "datacite" }, "oai": { "identifier": "oai:zenodo.org:20615690", "provider": "oai" } }, "revision_id": 6, "stats": { "all_versions": { "data_volume": 5842494.0, "downloads": 3, "unique_downloads": 3, "unique_views": 17, "views": 18 }, "this_version": { "data_volume": 5842494.0, "downloads": 3, "unique_downloads": 3, "unique_views": 17, "views": 18 } }, "status": "published", "swh": {}, "updated": "2026-06-09T17:38:25.681348+00:00", "versions": { "index": 1, "is_latest": true } }