Triple
T31224771
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cold War-era Royal Navy |
E796108
|
entity |
| Predicate | maintainedCapability |
P56209
|
FINISHED |
| Object | blue-water navy |
—
|
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: blue-water navy | Statement: [Cold War-era Royal Navy, maintainedCapability, blue-water navy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maintainedCapability Context triple: [Cold War-era Royal Navy, maintainedCapability, blue-water navy]
-
A.
plannedCapability
Indicates that an entity is intended or scheduled to possess or provide a particular capability in the future.
-
B.
consideredCapability
Indicates that something is regarded or evaluated as a potential capability of an entity.
-
C.
demonstratedCapability
Indicates that an entity has shown, through evidence or performance, the ability to carry out a specific action or function.
-
D.
associatedCapability
chosen
Indicates that one entity has a related ability, function, or competence that is linked to or relevant for another entity.
-
E.
usedCapability
Indicates that an entity employed or exercised a particular capability, skill, or function in performing an action or achieving a result.
- 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_69f224da98f88190ab32f690cce5d303 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f757898fe48190b124dc7301672623 |
completed | May 3, 2026, 2:11 p.m. |
| PD | Predicate disambiguation | batch_69f754c484348190948d2a04ff228fb1 |
completed | May 3, 2026, 1:59 p.m. |
Created at: April 29, 2026, 9:10 p.m.