Triple
T36346079
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Percheron horse |
E895067
|
entity |
| Predicate | coatColorPolicy |
P161534
|
FINISHED |
| Object | some studbooks restrict registration to black and gray |
—
|
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: some studbooks restrict registration to black and gray | Statement: [Percheron horse, coatColorPolicy, some studbooks restrict registration to black and gray]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coatColorPolicy Context triple: [Percheron horse, coatColorPolicy, some studbooks restrict registration to black and gray]
-
A.
coatColorRestriction
chosen
Indicates a constraint or rule specifying which coat colors are allowed or disallowed for an entity.
-
B.
coatColorSymbol
Indicates the symbolic or coded representation used to denote an entity’s coat color in a standardized form.
-
C.
hoodColor
Indicates the color attribute specifically of an entity’s hood (e.g., the hood of a garment or vehicle).
-
D.
hasCapColor
Indicates that an entity possesses a cap whose color is specified by the related value.
-
E.
capeColor
Indicates the color attribute associated with a cape worn or possessed by an 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_69f76e4f437c8190a1af3ea2564f41f5 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7bb3ff1b08190802b1063d55d3923 |
completed | May 3, 2026, 9:16 p.m. |
| PD | Predicate disambiguation | batch_69f7b9a611a081908dd6aec1df3f4d7f |
completed | May 3, 2026, 9:09 p.m. |
Created at: May 3, 2026, 4:09 p.m.