Triple

T17709765
Position Surface form Disambiguated ID Type / Status
Subject Sviatoshynsko–Brovarska line E441531 entity
Predicate hasStation P35 FINISHED
Object Arsenalna NE NERFINISHED

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: Arsenalna | Statement: [Sviatoshynsko–Brovarska line, hasStation, Arsenalna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arsenalna
Context triple: [Sviatoshynsko–Brovarska line, hasStation, Arsenalna]
  • A. Arsenalna chosen
    Arsenalna is a Kyiv Metro station best known for being one of the deepest underground metro stations in the world.
  • B. The Arsenal
    The Arsenal is a historic 19th-century fortress-like building in New York City's Central Park that now serves as an administrative and exhibition space for the park and city parks department.
  • C. Arsenal
    Arsenal is a British anarcho-punk band known for its politically charged music and association with the 1980s underground punk scene.
  • D. Arsenal
    "Arsenal" is a 1929 Soviet silent film directed by Oleksandr Dovzhenko, renowned as a key work of the Soviet montage movement depicting the turmoil of the Ukrainian–Soviet War.
  • E. The Gunners
    The Gunners is the traditional nickname of the Royal Regiment of Artillery, a corps of the British Army responsible for providing artillery support.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9ea20b48190ace88bb46b01e6a9 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4729a9a9c81908d65ff0bda12c961 completed April 19, 2026, 6:13 a.m.
Created at: April 10, 2026, 10:05 a.m.