Triple

T13945988
Position Surface form Disambiguated ID Type / Status
Subject Frogfoot E335385 entity
Predicate aircraftNamedVariants P68743 FINISHED
Object Su-25UB E66858 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: Su-25UB | Statement: [Frogfoot, aircraftNamedVariants, Su-25UB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Su-25UB
Context triple: [Frogfoot, aircraftNamedVariants, Su-25UB]
  • A. Sukhoi Su-25 chosen
    The Sukhoi Su-25 is a Soviet-era, twin-engine, subsonic close air support aircraft designed for attacking ground targets in frontline combat.
  • B. Su-22
    The Su-22 is a Soviet-designed variable-sweep wing fighter-bomber widely exported and used for ground-attack missions by several air forces, including Poland’s.
  • C. Sukhoi Su-26
    The Sukhoi Su-26 is a Soviet/Russian single-seat aerobatic aircraft renowned for its exceptional maneuverability and success in international aerobatic competitions.
  • D. Sukhoi Su-33
    The Sukhoi Su-33 is a Russian carrier-based multirole fighter aircraft developed from the Su-27, optimized for naval operations with reinforced structure, folding wings, and specialized avionics.
  • E. Sukhoi Su-29
    The Sukhoi Su-29 is a Russian two-seat aerobatic training aircraft derived from the Su-26, widely used for advanced pilot instruction and competitive aerobatics.
  • 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_69d81c6081b88190b53e317c3370c8fe completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2e10f60c81908ee9636e85c070ff completed April 14, 2026, 12:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd949b9fc481908c7717c412e05fac completed May 8, 2026, 7:45 a.m.
Created at: April 9, 2026, 10:17 p.m.