Triple

T19096449
Position Surface form Disambiguated ID Type / Status
Subject Kenya Air Force E467417 entity
Predicate aircraft P2541 FINISHED
Object T-37 Tweet NE NERFINISHED

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: T-37 Tweet | Statement: [Kenya Air Force, aircraft, T-37 Tweet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: T-37 Tweet
Context triple: [Kenya Air Force, aircraft, T-37 Tweet]
  • A. Cessna T-37 Tweet chosen
    The Cessna T-37 Tweet is a small, twin‑engine jet trainer aircraft used extensively by the U.S. Air Force and several allied nations for primary pilot training during the Cold War era.
  • B. T-38 Talon
    The T-38 Talon is a twin-engine supersonic jet trainer aircraft widely used by air forces, particularly the U.S. Air Force, for advanced pilot training.
  • C. Beechcraft T-6 Texan II
    The Beechcraft T-6 Texan II is a single-engine turboprop military trainer aircraft widely used by air forces for primary and basic flight training.
  • D. Boeing T-7A Red Hawk
    The Boeing T-7A Red Hawk is a modern U.S. Air Force advanced jet trainer designed to prepare pilots for fifth-generation fighters like the F-22 and F-35.
  • E. Beechcraft T-34 Mentor
    The Beechcraft T-34 Mentor is a propeller-driven military trainer aircraft widely used by the U.S. and allied air forces for primary flight training from the 1950s onward.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8dd05ac4c8190b1967d8f97f3fb2f completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e369aeac81908913c21f4c234c8e completed April 20, 2026, 8:27 a.m.
Created at: April 10, 2026, 12:04 p.m.