Triple
T2385225
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Royal Navy officers |
E48803
|
entity |
| Predicate | canSpecialiseIn |
P466
|
FINISHED |
| Object | warfare branch |
—
|
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: warfare branch | Statement: [Royal Navy officers, canSpecialiseIn, warfare branch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canSpecialiseIn Context triple: [Royal Navy officers, canSpecialiseIn, warfare branch]
-
A.
hasSpecialty
chosen
Indicates that an entity possesses a particular area of expertise, focus, or professional specialization.
-
B.
hasSpecial
Indicates that an entity possesses or is associated with a distinctive or exceptional attribute, status, or feature compared to others.
-
C.
canBe
Indicates that one entity has the potential, permission, or capability to become, perform as, or be classified as another entity.
-
D.
hasCompetence
Indicates that an entity possesses the ability, skill, or qualification to perform a specific task or function effectively.
-
E.
canBelongTo
Indicates that something is capable of being a member or part of a particular group, category, or owner.
- 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_69a88aa5f63081908d07fd302029fcbd |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc7d8a918819089a210e74e13be6e |
completed | March 7, 2026, 6:38 a.m. |
| PD | Predicate disambiguation | batch_69abc59f73f08190924a36d7d475d8f4 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:57 p.m.