Triple
T2708386
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Auxey-Duresses |
E59797
|
entity |
| Predicate | typicalWhiteProfile |
P38941
|
FINISHED |
| Object | fresh mineral Chardonnay |
—
|
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: fresh mineral Chardonnay | Statement: [Auxey-Duresses, typicalWhiteProfile, fresh mineral Chardonnay]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalWhiteProfile Context triple: [Auxey-Duresses, typicalWhiteProfile, fresh mineral Chardonnay]
-
A.
whitePoint
Indicates the reference color point or standard white used as a basis for color measurements or calibration in a color space.
-
B.
typicalColorDescription
chosen
Indicates the usual or characteristic color associated with an entity.
-
C.
whitePointCCT
Indicates the correlated color temperature value that defines the white point reference for a color space or imaging system.
-
D.
typicalTexture
Indicates the usual or characteristic surface feel or consistency that is commonly associated with an entity.
-
E.
typicalBlendStyle
Indicates the usual or characteristic way in which two or more elements are combined or mixed together.
- 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_69ab4ac92a088190bc74bca14038e3de |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abda73de1c81908f5d6b0383e23144 |
completed | March 7, 2026, 7:57 a.m. |
| PD | Predicate disambiguation | batch_69abd8224c688190bb4a362360b03007 |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:55 p.m.