Triple
T4749504
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Admiral of the Blue |
E105442
|
entity |
| Predicate | doctrineContext |
P17738
|
FINISHED |
| Object | line-of-battle tactics |
—
|
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: line-of-battle tactics | Statement: [Admiral of the Blue, doctrineContext, line-of-battle tactics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: doctrineContext Context triple: [Admiral of the Blue, doctrineContext, line-of-battle tactics]
-
A.
doctrineName
Indicates that one entity is the formal or recognized name of a particular doctrine associated with another entity.
-
B.
usesDoctrine
Indicates that one entity applies, follows, or relies on a particular doctrine in its actions or reasoning.
-
C.
doctrineFocus
chosen
Indicates that a doctrine, teaching, or belief is primarily concerned with, centered on, or directed toward a particular subject or theme.
-
D.
doctrineType
Indicates that one entity is a classification or kind of doctrinal position, teaching, or belief system to which the other entity belongs or pertains.
-
E.
doctrineSourceFor
Indicates that one entity serves as the originating basis or authoritative source of doctrine, teachings, or principles for another entity.
- 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_69bd43f07fa48190954317d01600994a |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd64c6f5ac81908a62f9c17e77ac86 |
completed | March 20, 2026, 3:16 p.m. |
| PD | Predicate disambiguation | batch_69bd6223defc8190823665a6592c1154 |
completed | March 20, 2026, 3:05 p.m. |
Created at: March 20, 2026, 1:20 p.m.