Triple
T31507400
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Trident successor programme |
E803854
|
entity |
| Predicate | submarineClassName |
P171713
|
FINISHED |
| Object | Dreadnought-class submarine |
—
|
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: Dreadnought-class submarine | Statement: [Trident successor programme, submarineClassName, Dreadnought-class submarine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: submarineClassName Context triple: [Trident successor programme, submarineClassName, Dreadnought-class submarine]
-
A.
submarineClassLeadShip
Indicates that one entity is the lead (first-built or first-commissioned) ship of a particular submarine class represented by the other entity.
-
B.
submarineClassRole
Indicates the functional role or mission type assigned to a particular class of submarines within a naval context.
-
C.
primarySubmarineClassSupported
Indicates that an entity is designed to support, service, or operate primarily with a specific class of submarines.
-
D.
submarine
Indicates that one entity is a submarine in relation to another entity or context.
-
E.
submarineOnDisplay
Indicates that a submarine is being publicly exhibited, typically in a museum or similar display setting.
- F. None of above. chosen
Provenance (4 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_69f348ceb0a48190ae7feca263b6296c |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a21826308190b12c2e8d6ab218d5 |
completed | May 3, 2026, 1:17 a.m. |
| PD | Predicate disambiguation | batch_69f69fe82e5c81909da9db0a2f3bba6d |
completed | May 3, 2026, 1:07 a.m. |
| PDg | Predicate description generation | batch_69f6a0e920cc8190a943fdd0594906c5 |
completed | May 3, 2026, 1:12 a.m. |
Created at: April 30, 2026, 9:48 p.m.