Triple

T17894522
Position Surface form Disambiguated ID Type / Status
Subject Russian nuclear triad E447398 entity
Predicate airLegPlatform P129209 FINISHED
Object Tupolev Tu-22M3 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: Tupolev Tu-22M3 | Statement: [Russian nuclear triad, airLegPlatform, Tupolev Tu-22M3]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tupolev Tu-22M3
Context triple: [Russian nuclear triad, airLegPlatform, Tupolev Tu-22M3]
  • A. Tupolev Tu-22 bomber chosen
    The Tupolev Tu-22 is a Soviet-era supersonic long-range bomber designed during the Cold War for high-speed strike missions against strategic targets.
  • B. 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.
  • C. R-20 Rahe
    R-20 Rahe is an Estonian multiple rocket launcher system used by the Estonian Defence Forces.
  • D. 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.
  • E. 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.
  • 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_69d8b9f59bd48190a6fc925a855b8bac completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49d7ccf808190b4c1fd477043bcc8 completed April 19, 2026, 9:16 a.m.
Created at: April 10, 2026, 10:19 a.m.