Triple

T16663201
Position Surface form Disambiguated ID Type / Status
Subject Dowty Rotol E404911 entity
Predicate hasCustomer P734 FINISHED
Object ATR E219287 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: ATR | Statement: [Dowty Rotol, hasCustomer, ATR]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ATR
Context triple: [Dowty Rotol, hasCustomer, ATR]
  • A. ATR chosen
    ATR is a Franco-Italian aircraft manufacturer best known for producing regional turboprop airliners widely used by airlines around the world.
  • B. ATR
    ATR is a high-flux nuclear research reactor at Idaho National Laboratory used primarily for materials testing and irradiation experiments.
  • C. ATR
    ATR is the commonly used abbreviation for the Andaman Trunk Road, a major roadway running through the Andaman Islands in India.
  • D. ATR 72
    The ATR 72 is a twin-engine turboprop regional airliner widely used by airlines around the world for short-haul passenger flights.
  • E. ATR 42
    The ATR 42 is a twin-turboprop, short-haul regional airliner developed by the French-Italian manufacturer ATR, widely used by airlines for commuter and regional routes.
  • 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_69d8838b5fbc81908c6575c132b82e80 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e37c9afd048190b73bbc9c423915ca completed April 18, 2026, 12:44 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0084d091e0819088a98ef4aa775d07 completed May 10, 2026, 1:14 p.m.
Created at: April 10, 2026, 5:18 a.m.