Triple

T8455317
Position Surface form Disambiguated ID Type / Status
Subject H160 E199904 entity
Predicate manufacturer P490 FINISHED
Object Airbus Group E6021 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 Group | Statement: [H160, manufacturer, Airbus Group]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Airbus Group
Context triple: [H160, manufacturer, Airbus Group]
  • A. Airbus chosen
    Airbus is a major European aerospace corporation known for designing and manufacturing commercial airliners such as the A320, A330, and A380 families.
  • B. EADS
    EADS (European Aeronautic Defence and Space Company) was a major European aerospace and defense corporation that later became part of Airbus Group.
  • C. Airbus Transport International
    Airbus Transport International is a specialized cargo airline that operates Airbus Beluga aircraft to transport oversized aircraft components and other outsize freight for Airbus and its partners.
  • D. Aérospatiale
    Aérospatiale was a major French aerospace manufacturer and state-owned company that played a key role in European aviation and space projects, including as a founding partner of Airbus.
  • E. The Safran Company
    The Safran Company is a film and television production company best known for producing major horror franchises such as The Conjuring series.
  • 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_69ca8318231881908fd1bc1c4d45d286 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe48e0ae481908b40f7f124b0551e completed March 31, 2026, 3:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69cea82c897c8190b7554d2e91968b53 completed April 2, 2026, 5:32 p.m.
Created at: March 30, 2026, 6:10 p.m.