Triple

T8130625
Position Surface form Disambiguated ID Type / Status
Subject FV432 E189843 entity
Predicate manufacturer P490 FINISHED
Object GKN Sankey E36248 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: GKN Sankey | Statement: [FV432, manufacturer, GKN Sankey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: GKN Sankey
Context triple: [FV432, manufacturer, GKN Sankey]
  • A. GKN Sankey chosen
    GKN Sankey was a British engineering and manufacturing company best known for producing military vehicles and automotive components.
  • B. Power Jets Ltd
    Power Jets Ltd was a pioneering British company founded to develop and commercialize Frank Whittle’s early jet engine designs, playing a crucial role in the birth of jet propulsion.
  • C. Bristol Siddeley
    Bristol Siddeley was a British aero engine manufacturer known for developing innovative jet and turbofan engines before its merger into Rolls-Royce.
  • D. Armstrong Siddeley
    Armstrong Siddeley was a British engineering company best known for manufacturing luxury automobiles and aircraft engines in the early to mid-20th century.
  • E. Turbomeca
    Turbomeca is a French aerospace company renowned for designing and producing small and medium gas turbine engines, particularly for helicopters and military aircraft.
  • 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_69ca82bcb4848190a9a9d036ad768642 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb43b7dbd881908a80f23090596eae completed March 31, 2026, 3:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc947a7354819088c6f3cc6ab677cf completed April 1, 2026, 3:43 a.m.
Created at: March 30, 2026, 5:34 p.m.