Triple

T14059688
Position Surface form Disambiguated ID Type / Status
Subject Kékes E338310 entity
Predicate locatedIn P40 FINISHED
Object Mátra E844209 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: Mátra | Statement: [Kékes, locatedIn, Mátra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mátra
Context triple: [Kékes, locatedIn, Mátra]
  • A. Mátra Mountains chosen
    The Mátra Mountains are a volcanic mountain range in northern Hungary known for hosting the country’s highest peak, Kékes, and popular hiking and ski areas.
  • B. Zemplén Mountains
    The Zemplén Mountains are a volcanic mountain range in northeastern Hungary and southeastern Slovakia, known for their forested landscapes, castles, and wine-producing regions.
  • C. Mecsek Mountains
    The Mecsek Mountains are a low, forested mountain range in southern Hungary known for their scenic hiking trails, caves, and vineyards.
  • D. Upper Zemplín
    Upper Zemplín is a northeastern subregion of the historical Zemplín area in Slovakia, known for its mountainous landscapes, forests, and traditional rural culture.
  • E. Bakony Mountains
    The Bakony Mountains are a forested mountain range in western Hungary, forming part of the Transdanubian Mountains and known for their karst landscapes, hiking trails, and natural beauty.
  • 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_69d81c67ba6c819091935650dfb3b895 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de5686f51c81908c33143ecbaae83d completed April 14, 2026, 3 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcb662c37c8190a629278a97060080 completed May 7, 2026, 3:57 p.m.
Created at: April 9, 2026, 10:21 p.m.