Triple

T18274159
Position Surface form Disambiguated ID Type / Status
Subject Zenit E437690 entity
Predicate manufacturer P490 FINISHED
Object Yuzhmash 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: Yuzhmash | Statement: [Zenit, manufacturer, Yuzhmash]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yuzhmash
Context triple: [Zenit, manufacturer, Yuzhmash]
  • A. Yuzhmash chosen
    Yuzhmash is a major Ukrainian aerospace and defense manufacturer known for producing ballistic missiles, space launch vehicles, and rocket technology.
  • B. Yuzhnoye Design Bureau
    Yuzhnoye Design Bureau is a Ukrainian aerospace and rocket design organization renowned for developing ballistic missiles and space launch vehicles for the former Soviet Union and modern Ukraine.
  • C. Yuzhnoye MCC station
    Yuzhnoye MCC station is a passenger railway stop on Moscow’s orbital Moscow Central Circle urban rail line.
  • D. NPO Energomash
    NPO Energomash is a leading Russian rocket engine design and manufacturing company renowned for producing powerful liquid-fueled engines used in launch vehicles worldwide.
  • E. Almaz Central Design Bureau
    Almaz Central Design Bureau is a Russian defense design organization best known for developing advanced surface-to-air missile systems and air defense technologies.
  • 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_69d8b914530c8190b4474d862a2b2a1b completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e50050d6688190b909a1c24e1dd3c9 completed April 19, 2026, 4:18 p.m.
Created at: April 10, 2026, 10:34 a.m.