Triple

T11617617
Position Surface form Disambiguated ID Type / Status
Subject Haitian Air Force E275549 entity
Predicate operatedAircraft P1524 FINISHED
Object Cessna 172 E869615 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: Cessna 172 | Statement: [Haitian Air Force, operatedAircraft, Cessna 172]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cessna 172
Context triple: [Haitian Air Force, operatedAircraft, Cessna 172]
  • A. Cessna 172 chosen
    The Cessna 172 is a four-seat, single-engine, high-wing light aircraft widely used worldwide for flight training and personal aviation.
  • B. Cessna 152
    The Cessna 152 is a popular two-seat, single-engine light aircraft widely used around the world for pilot training and recreational flying.
  • C. Cessna 182
    The Cessna 182 is a popular four-seat, single-engine light aircraft known for its reliability, versatility, and use in personal, training, and utility flying.
  • D. Cessna 150
    The Cessna 150 is a popular two-seat, single-engine light aircraft widely used around the world for flight training and personal flying.
  • E. Beechcraft Bonanza
    The Beechcraft Bonanza is a long-running, high-performance single-engine general aviation aircraft renowned for its distinctive V-tail (in early models) and popularity among private pilots.
  • 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_69d6aaf84b548190ac072e4fb89ae18f completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a047758081908191c1d564409d9a completed April 10, 2026, 7:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69f457dc01ec8190a7ee3108d4d95957 completed May 1, 2026, 7:35 a.m.
Created at: April 8, 2026, 9:38 p.m.