Triple

T2251801
Position Surface form Disambiguated ID Type / Status
Subject Sudetes E49632 entity
Predicate hasCity P316 FINISHED
Object Jelenia Góra E307156 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: Jelenia Góra | Statement: [Sudetes, hasCity, Jelenia Góra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jelenia Góra
Context triple: [Sudetes, hasCity, Jelenia Góra]
  • A. Jelenia Góra chosen
    Jelenia Góra is a historic city in southwestern Poland, known for its picturesque setting in the Karkonosze Mountains and its well-preserved old town architecture.
  • B. Zielona Góra
    Zielona Góra is a city in western Poland known for its wine-making tradition and annual wine festival.
  • C. Glogów
    Glogów is a historic town in western Poland on the Oder River, known for its medieval origins and reconstructed Old Town.
  • D. Polkowice
    Polkowice is a town in southwestern Poland known for its copper mining industry and location within the Lower Silesian region.
  • E. Inowrocław
    Inowrocław is a historic spa and industrial city in north-central Poland, known for its saltworks and location in the Kuyavia region.
  • 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_69a88aaa9250819095e127d0d77e8a32 completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc11d04688190abc04fac3a1804a9 completed March 7, 2026, 6:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69b51c512b108190b08245662695b8ca completed March 14, 2026, 8:29 a.m.
Created at: March 4, 2026, 7:47 p.m.