Triple

T11703550
Position Surface form Disambiguated ID Type / Status
Subject Galanta E278181 entity
Predicate hasTwinTown P919 FINISHED
Object Hodonín E419333 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: Hodonín | Statement: [Galanta, hasTwinTown, Hodonín]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hodonín
Context triple: [Galanta, hasTwinTown, Hodonín]
  • A. Hodonín chosen
    Hodonín is a town in the South Moravian Region of the Czech Republic, notable as the birthplace of the first Czechoslovak president Tomáš Garrigue Masaryk.
  • B. Husinec
    Husinec is a small Czech town best known as the birthplace of the religious reformer Jan Hus.
  • C. Borohrádek
    Borohrádek is a small town in the Hradec Králové Region of the Czech Republic.
  • D. Moravice
    Moravice is a river in the northern part of the historical Moravia region of the Czech Republic.
  • E. Bohdašín
    Bohdašín is a small village in the Hradec Králové Region of the Czech Republic, administratively belonging to the town of Teplice nad Metují.
  • 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_69d6aaff2ce88190b4a1e4b341ad5377 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a49b1080819096593733ee48a187 completed April 10, 2026, 7:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69ef83525ae081909ee6f3fbb5d37dd7 completed April 27, 2026, 3:40 p.m.
Created at: April 8, 2026, 9:40 p.m.