Triple

T8693909
Position Surface form Disambiguated ID Type / Status
Subject Training Air Wing FIVE E206357 entity
Predicate aircraftUsed P1524 FINISHED
Object TH-73A Thrasher E751040 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: TH-73A Thrasher | Statement: [Training Air Wing FIVE, aircraftUsed, TH-73A Thrasher]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: TH-73A Thrasher
Context triple: [Training Air Wing FIVE, aircraftUsed, TH-73A Thrasher]
  • A. TH-73A Thrasher chosen
    The TH-73A Thrasher is a modern training helicopter used by the U.S. Navy to prepare student aviators for advanced rotary-wing operations.
  • B. SA-17 Grizzly
    SA-17 Grizzly is the NATO reporting name for a Russian-made, medium-range, mobile surface-to-air missile system designed to engage aircraft, cruise missiles, and other aerial threats.
  • C. HC-27J Spartan
    The HC-27J Spartan is a medium-range, twin-engine turboprop aircraft used by the U.S. Coast Guard for missions such as search and rescue, maritime patrol, and transport.
  • D. T-Rac
    T-Rac is the raccoon-themed costumed mascot of the NFL’s Tennessee Titans, known for his energetic antics and fan engagement at games and events.
  • E. Thurbo
    Thurbo is a Swiss regional railway company that operates local and suburban train services, particularly in northeastern Switzerland.
  • 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_69ca835481fc819084e33d3bc883bfa6 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5826bbb48190a212fb1bb06e05e6 completed March 31, 2026, 11:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf28958ba481908383e31802ce2093 completed April 3, 2026, 2:40 a.m.
Created at: March 30, 2026, 6:33 p.m.