Triple

T22040663
Position Surface form Disambiguated ID Type / Status
Subject Aviadvigatel PS-90A E544628 entity
Predicate hasVariant P455 FINISHED
Object PS-90A2 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: PS-90A2 | Statement: [Aviadvigatel PS-90A, hasVariant, PS-90A2]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: PS-90A2
Context triple: [Aviadvigatel PS-90A, hasVariant, PS-90A2]
  • A. PS-90A chosen
    The PS-90A is a Russian high-bypass turbofan aircraft engine widely used on modernized versions of Ilyushin and Tupolev airliners.
  • B. PZ-90
    PZ-90 is a geodetic coordinate reference system used by the Russian GLONASS satellite navigation system to define positions on Earth.
  • C. A90
    A90 is the orbital motorway encircling Rome, Italy, serving as a major ring road for traffic around the city.
  • D. A90
    The A90 is a major trunk road in eastern Scotland that connects Edinburgh to Perth and continues north toward Dundee and Aberdeen.
  • E. LM-900
    The LM-900 is a commercial satellite bus platform developed by Lockheed Martin and used as the structural and systems foundation for various spacecraft, including scientific missions like WMAP.
  • 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_69e11e32445c8190ab97089b48a130bb completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f12828fc788190a22c0e9c2372656b completed April 28, 2026, 9:35 p.m.
Created at: April 16, 2026, 8:25 p.m.