Triple

T2705879
Position Surface form Disambiguated ID Type / Status
Subject Ariane 5 ECA E59340 entity
Predicate manufacturer P490 FINISHED
Object Safran E131994 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: Safran | Statement: [Ariane 5 ECA, manufacturer, Safran]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Safran
Context triple: [Ariane 5 ECA, manufacturer, Safran]
  • A. Safran chosen
    Safran is a major French multinational company specializing in aerospace, defense, and security technologies.
  • B. 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.
  • C. Syrian Air
    Syrian Air is the state-owned national airline of Syria, operating regional and international passenger flights primarily from its hub in Damascus.
  • D. MTU Aero Engines
    MTU Aero Engines is a leading German aircraft engine manufacturer specializing in the development, production, and maintenance of military and commercial aero engines.
  • E. Safran Arriel 2E
    The Safran Arriel 2E is a modern turboshaft engine designed for light twin-engine helicopters, offering improved power, fuel efficiency, and reliability over earlier Arriel variants.
  • 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_69ab4ac66bc88190b9e4afa5fc843f72 completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abda559a908190ad5d92c11a398a03 completed March 7, 2026, 7:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69afaf7c22a4819096ff9effe9e0d77d completed March 10, 2026, 5:43 a.m.
Created at: March 6, 2026, 9:55 p.m.