Triple
T29053858
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Constable (New Zealand police rank) |
E735335
|
entity |
| Predicate | uniformedOrPlainclothes |
P165963
|
FINISHED |
| Object | uniformed |
—
|
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: uniformed | Statement: [Constable (New Zealand police rank), uniformedOrPlainclothes, uniformed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: uniformedOrPlainclothes Context triple: [Constable (New Zealand police rank), uniformedOrPlainclothes, uniformed]
-
A.
usedPlainClothes
Indicates that an entity carried out an action or role while wearing ordinary, non-uniform clothing to avoid being recognized in an official capacity.
-
B.
woreUniformOf
Indicates that one entity was dressed in or used the official uniform associated with another entity (such as an organization, group, or role).
-
C.
wearsOnUniform
Indicates that an item is part of and is worn as a component of a uniform.
-
D.
wearsUniformSimilarTo
Indicates that one entity wears a uniform that is similar in appearance or style to the uniform worn by another entity.
-
E.
wearsSpecialUniforms
Indicates that an entity regularly wears distinctive or non-standard uniforms associated with a particular role, group, or occasion.
- F. None of above. chosen
Provenance (4 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_69f077e64b88819094d37bdbca8191b3 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f66067f58c819087237fa88ad513cb |
completed | May 2, 2026, 8:36 p.m. |
| PD | Predicate disambiguation | batch_69f659d297cc8190b2b962ba30a1edb3 |
completed | May 2, 2026, 8:08 p.m. |
| PDg | Predicate description generation | batch_69f65ad638ac8190a17bb987fce53279 |
completed | May 2, 2026, 8:13 p.m. |
Created at: April 28, 2026, 10:10 a.m.