Triple

T8670049
Position Surface form Disambiguated ID Type / Status
Subject U-28A Draco E205771 entity
Predicate basedOn P98 FINISHED
Object Pilatus PC-12 E593335 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: Pilatus PC-12 | Statement: [U-28A Draco, basedOn, Pilatus PC-12]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pilatus PC-12
Context triple: [U-28A Draco, basedOn, Pilatus PC-12]
  • A. Pilatus PC-12 chosen
    The Pilatus PC-12 is a Swiss single-engine turboprop aircraft renowned for its versatility, combining executive transport, cargo, and commuter roles with short takeoff and landing capability.
  • B. Pilatus PC-21
    The Pilatus PC-21 is a Swiss-made, next-generation turboprop military trainer aircraft designed to provide jet-like performance and advanced training capabilities for fighter pilots.
  • C. Pilatus PC-9
    The Pilatus PC-9 is a Swiss-built turboprop training aircraft widely used by military air forces around the world for basic and advanced pilot instruction.
  • D. Pilatus PC-7
    The Pilatus PC-7 is a Swiss-built turboprop military trainer aircraft widely used for basic flight training by air forces around the world.
  • E. Pilatus PC-24
    The Pilatus PC-24 is a Swiss-made light business jet known for its ability to operate from short and unpaved runways while offering a spacious, versatile cabin.
  • 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_69ca83516ae88190aefe034b3bc589e3 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc4917cb9881909a73b74e54250613 completed March 31, 2026, 10:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69cecd2b996481908da33fbd95494376 completed April 2, 2026, 8:10 p.m.
Created at: March 30, 2026, 6:31 p.m.