Triple
T18264197
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bouvier des Flandres |
E437439
|
entity |
| Predicate | coatAppearance |
P48712
|
FINISHED |
| Object | tousled |
—
|
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: tousled | Statement: [Bouvier des Flandres, coatAppearance, tousled]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coatAppearance Context triple: [Bouvier des Flandres, coatAppearance, tousled]
-
A.
coatCharacteristic
chosen
Indicates that one entity has a particular property, feature, or quality that characterizes its outer covering or surface.
-
B.
fashionCharacteristic
Indicates a relationship where one entity possesses or exhibits a particular style, trend, or fashion-related attribute in relation to another.
-
C.
colorOfApparel
Indicates the specific color attribute associated with a piece of apparel or clothing item.
-
D.
dressColor
Indicates the color attribute associated with a particular dress.
-
E.
appearance
Indicates how something looks or seems to an observer, including its visible form, condition, or outward impression.
- 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_69d8b913351c8190932b6a426de04b41 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4ff78b188819081da8e1d389c6c79 |
completed | April 19, 2026, 4:14 p.m. |
| PD | Predicate disambiguation | batch_69e44fcdee748190bae6fb76e0cb22f3 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:34 a.m.