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.