Triple

T3746257
Position Surface form Disambiguated ID Type / Status
Subject Short Brothers E81217 entity
Predicate parentCompany P254 FINISHED
Object Bombardier Aerospace E97324 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: Bombardier Aerospace | Statement: [Short Brothers, parentCompany, Bombardier Aerospace]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bombardier Aerospace
Context triple: [Short Brothers, parentCompany, Bombardier Aerospace]
  • A. Bombardier chosen
    Bombardier is a major Canadian manufacturer of trains and rail equipment widely used by transit agencies around the world.
  • B. de Havilland Aircraft Company
    De Havilland Aircraft Company was a major British aviation manufacturer renowned for designing innovative military and civilian aircraft, including iconic World War II planes.
  • C. Textron Aviation
    Textron Aviation is a major American aircraft manufacturer known for producing Cessna and Beechcraft airplanes for business, general aviation, and special mission use.
  • D. Spirit AeroSystems
    Spirit AeroSystems is one of the world’s largest non-OEM designers and manufacturers of aerostructures for commercial and defense aircraft.
  • E. Gulfstream Aerospace
    Gulfstream Aerospace is an American manufacturer renowned for its high-performance business jets used by corporate, government, and private clients worldwide.
  • 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_69ad8b19b7b08190a6188804e99c53e9 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adcb680ddc819094205beb342699f9 completed March 8, 2026, 7:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4db2c2c5081909b83d89c989a8d1c completed March 14, 2026, 3:51 a.m.
Created at: March 8, 2026, 3:35 p.m.