Triple

T10092741
Position Surface form Disambiguated ID Type / Status
Subject Northern Hungary E215782 entity
Predicate containsTown P847 FINISHED
Object Tokaj E234399 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Tokaj | Statement: [Northern Hungary, containsTown, Tokaj]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tokaj
Context triple: [Northern Hungary, containsTown, Tokaj]
  • A. Tokaj chosen
    Tokaj is a historic town in northeastern Hungary renowned worldwide for its Tokaji wine region and sweet dessert wines.
  • B. Sopron wine region
    Sopron wine region is a historic Hungarian wine-producing area near the Austrian border, known especially for its Kékfrankos (Blaufränkisch) red wines.
  • C. Villány
    Villány is a small town in southern Hungary renowned as one of the country’s premier wine regions, especially famous for its red wines.
  • D. Makó
    Makó is a town in southeastern Hungary, renowned for its onion production and thermal baths.
  • E. Kaposvár
    Kaposvár is a city in southwestern Hungary that serves as the administrative and cultural center of Somogy County.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69ca83a4947c8190823a7495dc5d96ed completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cdd05c3c0c8190927580717429a4e5 completed April 2, 2026, 2:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69d30050fbec8190ab7807d64ab73e61 completed April 6, 2026, 12:37 a.m.
Created at: March 30, 2026, 9:01 p.m.