Triple

T14040131
Position Surface form Disambiguated ID Type / Status
Subject Flanker E337823 entity
Predicate hasVariant P455 FINISHED
Object Su-33 E359882 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-33 | Statement: [Flanker, hasVariant, Su-33]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Su-33
Context triple: [Flanker, hasVariant, Su-33]
  • A. Sukhoi Su-33 chosen
    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.
  • B. Sukhoi Su-31
    The Sukhoi Su-31 is a Russian single-seat aerobatic aircraft renowned for its high maneuverability and use in advanced competition flying.
  • C. Sukhoi Su‑34
    The Sukhoi Su‑34 is a Russian twin-engine, twin-seat fighter-bomber designed for long-range precision strike missions with advanced avionics and all-weather capability.
  • D. Sukhoi Su-30
    The Sukhoi Su-30 is a twin-engine, multirole Russian fighter aircraft known for its long-range, high maneuverability, and advanced air-to-air and air-to-ground capabilities.
  • E. Su-39
    The Su-39 is a modernized Russian close air support and anti-tank aircraft developed from the Su-25, featuring enhanced avionics and weapon systems for improved battlefield effectiveness.
  • 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_69d81c664e48819088cbd8f433aeffe5 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de30ee374081908b6b5e8f81dd90f2 completed April 14, 2026, 12:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe64e47f1c8190a4ad09bc96d35b69 completed May 8, 2026, 10:34 p.m.
Created at: April 9, 2026, 10:20 p.m.