Triple

T7025173
Position Surface form Disambiguated ID Type / Status
Subject Alexander Antonov E162926 entity
Predicate familyName P18 FINISHED
Object Antonov E558971 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: Antonov | Statement: [Alexander Antonov, familyName, Antonov]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Antonov
Context triple: [Alexander Antonov, familyName, Antonov]
  • A. Antonov chosen
    Antonov is a Ukrainian aerospace company best known for designing and producing large cargo and passenger aircraft, including some of the world’s heaviest and largest planes.
  • B. Tupolev
    Tupolev is a Russian aerospace and defense company best known for designing and producing military and civilian aircraft, including strategic bombers and airliners.
  • C. Antonov Design Bureau
    Antonov Design Bureau is a Ukrainian aerospace company renowned for designing and producing large cargo and passenger aircraft, including some of the world’s heaviest transport planes.
  • D. Antonov An-158 (historically)
    The Antonov An-158 is a Ukrainian-designed regional jet airliner, developed as a stretched variant of the An-148 to carry more passengers on short- to medium-haul routes.
  • E. Antonov An-10
    The Antonov An-10 is a Soviet-era four-engine turboprop airliner that was also adapted for military transport roles.
  • 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_69c6885b26248190a857541e3d10e299 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6e1fb8f0c8190b15dd7ce7ab6a8f2 completed March 27, 2026, 8 p.m.
NED1 Entity disambiguation (via context triple) batch_69c77581e2a88190ad2ec9855772c6a5 completed March 28, 2026, 6:30 a.m.
Created at: March 27, 2026, 2:35 p.m.