Triple
T14694038
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Resolution-class submarines |
E345106
|
entity |
| Predicate | deterrentRoleStart |
P55565
|
FINISHED |
| Object | late 1960s |
—
|
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: late 1960s | Statement: [Resolution-class submarines, deterrentRoleStart, late 1960s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: deterrentRoleStart Context triple: [Resolution-class submarines, deterrentRoleStart, late 1960s]
-
A.
deterrentPosture
Indicates a stance or set of actions intended to discourage or prevent another party from taking hostile or undesired actions.
-
B.
startingGuard
Indicates that an entity serves as the primary or first-choice guard in a lineup, formation, or configuration.
-
C.
laterEnforcementRole
Indicates that an entity assumes or is assigned an enforcement-related role at a later time relative to another role, event, or time period.
-
D.
securityApparatusRole
Indicates the role or function an entity holds within a security or law-enforcement apparatus.
-
E.
startOfDefense
chosen
Indicates the point in time or event at which a defense or defensive action begins.
- 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_69d822e34b348190ada4d1cdb6c7c226 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb586e7108190be644db9cf9a4d99 |
completed | April 14, 2026, 9:45 p.m. |
| PD | Predicate disambiguation | batch_69de6579fb7881909becc8f5822b39d4 |
completed | April 14, 2026, 4:04 p.m. |
Created at: April 10, 2026, 1:28 a.m.