Triple

T15755558
Position Surface form Disambiguated ID Type / Status
Subject KC2 E381958 entity
Predicate basedOn P98 FINISHED
Object Airbus Voyager E85658 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: Airbus Voyager | Statement: [KC2, basedOn, Airbus Voyager]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Airbus Voyager
Context triple: [KC2, basedOn, Airbus Voyager]
  • A. Airbus Voyager chosen
    Airbus Voyager is a military air-to-air refuelling and transport aircraft used primarily by the Royal Air Force, based on the Airbus A330 platform.
  • B. Beechcraft Duchess
    The Beechcraft Duchess is a light twin-engine training and touring aircraft known for its reliability and use in multi-engine pilot instruction.
  • C. Rutan Voyager
    Rutan Voyager was the experimental aircraft that made the first nonstop, non-refueled flight around the world in 1986.
  • D. South African Airways Voyager
    South African Airways Voyager is the frequent-flyer loyalty program of South African Airways, offering members mileage accrual and tiered benefits for air travel and partner services.
  • E. Convair 880
    The Convair 880 was a narrow-body jet airliner introduced in the early 1960s, known for its high speed but limited commercial success compared to contemporaries like the Boeing 707.
  • 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_69d86d9e6b44819085d1f6a969ecb74c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e050b1ff4881909d5240d1d30f5c8b completed April 16, 2026, 3 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff87714a8481909f8489c73ac89c11 completed May 9, 2026, 7:13 p.m.
Created at: April 10, 2026, 4:47 a.m.