Triple

T23535495
Position Surface form Disambiguated ID Type / Status
Subject Star 48BV E576689 entity
Predicate manufacturer P490 FINISHED
Object Thiokol 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: Thiokol | Statement: [Star 48BV, manufacturer, Thiokol]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thiokol
Context triple: [Star 48BV, manufacturer, Thiokol]
  • A. Thiokol chosen
    Thiokol was an American aerospace and chemical company best known for manufacturing the solid rocket boosters used on NASA’s Space Shuttle.
  • B. Enerjet
    Enerjet was a Canadian low-cost charter airline that later rebranded and relaunched as Lynx Air, focusing on ultra-low-cost scheduled passenger services.
  • C. Yoyodyne
    Yoyodyne is a fictional aerospace and defense corporation that appears in various works of speculative fiction, often symbolizing opaque, technologically advanced, and morally ambiguous corporate power.
  • D. Aerojet General Nucleonics
    Aerojet General Nucleonics was a division of the aerospace and defense contractor Aerojet that specialized in nuclear and space-related technologies and training during the mid-20th century.
  • E. TVEL Fuel Company
    TVEL Fuel Company is a Russian nuclear fuel manufacturer and technology provider that supplies fuel assemblies and related services for nuclear power plants worldwide.
  • 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_69e245f5a8848190a2ba42e271c6c31f completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f1ae164f348190a6bde1a0dfc66389 completed April 29, 2026, 7:07 a.m.
Created at: April 17, 2026, 6:10 p.m.