Triple
T2417907
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | French Submarine Forces |
E52348
|
entity |
| Predicate | typeOfDeterrent |
P1135
|
FINISHED |
| Object | sea-based 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: sea-based nuclear deterrent | Statement: [French Submarine Forces, typeOfDeterrent, sea-based nuclear deterrent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfDeterrent Context triple: [French Submarine Forces, typeOfDeterrent, sea-based nuclear deterrent]
-
A.
restraintType
Indicates the specific kind or method of restraint applied in a given situation or relationship.
-
B.
typeOfDefense
chosen
Indicates the specific kind or category of defense employed or possessed in a given context.
-
C.
detectorType
Indicates the specific kind or category of detector associated with an entity or measurement.
-
D.
protectionType
Indicates the kind or method of protection that is applied to or associated with an entity.
-
E.
aimsToProtect
Indicates an intention or purpose to safeguard or defend one entity, value, or condition from harm, risk, or undesirable outcomes.
- 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_69ab495622948190bc6bc6e4cddaf645 |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abc9f342e88190a430b02842ded418 |
completed | March 7, 2026, 6:47 a.m. |
| PD | Predicate disambiguation | batch_69abc5a889948190b77de4ef6ac815a8 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 6, 2026, 9:42 p.m.