Triple

T9820293
Position Surface form Disambiguated ID Type / Status
Subject HMS Vengeance E238511 entity
Predicate nuclearDeterrent P3063 FINISHED
Object United Kingdom strategic nuclear deterrent LITERAL 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: United Kingdom strategic nuclear deterrent | Statement: [HMS Vengeance, nuclearDeterrent, United Kingdom strategic nuclear deterrent]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: nuclearDeterrent
Context triple: [HMS Vengeance, nuclearDeterrent, United Kingdom strategic nuclear deterrent]
  • A. nuclearCapability
    Indicates that an entity possesses, develops, or has access to nuclear weapons or the technological capacity to produce them.
  • B. nuclearWeaponsProgram
    Indicates the existence, development, or pursuit of a program related to the research, production, or maintenance of nuclear weapons.
  • C. positionOnNuclearWeapons
    Indicates a stance, policy, or viewpoint that an entity holds regarding the development, possession, use, or regulation of nuclear weapons.
  • D. hasNuclearWeapons chosen
    Indicates that the subject possesses or controls nuclear weapons.
  • E. nuclearWeaponsState
    Indicates that a state possesses, has developed, or is recognized as having nuclear weapons capabilities.
  • F. None of above.

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_69ca84dfde1481909f47c286d715f892 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdb313134081908eb0ba3a22b22e2b completed April 2, 2026, 12:06 a.m.
PD Predicate disambiguation batch_69cd03e01ea881909a7d93fc3994ace5 completed April 1, 2026, 11:39 a.m.
Created at: March 30, 2026, 8:31 p.m.