Triple
T35666
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Army Green Service Uniform |
E705
|
entity |
| Predicate | authorizedFor |
P1608
|
FINISHED |
| Object | male soldiers |
—
|
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: male soldiers | Statement: [Army Green Service Uniform, authorizedFor, male soldiers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: authorizedFor Context triple: [Army Green Service Uniform, authorizedFor, male soldiers]
-
A.
isGrantedFor
chosen
Indicates that a permission, right, or benefit has been formally given to a specific entity for a particular purpose or use.
-
B.
hasAccessTo
Indicates that one entity is permitted to enter, use, or interact with another entity, resource, or location.
-
C.
grantedTo
Indicates that a right, permission, or resource has been formally given or assigned by one party to another.
-
D.
hasRole
Indicates that an entity occupies, performs, or is assigned a specific role or function in relation to another entity or context.
-
E.
requiresPermitFor
Indicates that one entity must obtain formal permission or authorization before performing an action involving 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_69a2479dec388190967ba648663442c9 |
completed | Feb. 28, 2026, 1:40 a.m. |
| NER | Named-entity recognition | batch_69a24989c3308190af59dfae37cfc32f |
completed | Feb. 28, 2026, 1:48 a.m. |
| PD | Predicate disambiguation | batch_69a24873e97c8190b9e4279e43b6de14 |
completed | Feb. 28, 2026, 1:44 a.m. |
Created at: Feb. 28, 2026, 1:44 a.m.