Triple
T7608241
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pinot Teinturier |
E180162
|
entity |
| Predicate | distinctionFromOtherPinots |
P77756
|
FINISHED |
| Object | red flesh instead of white flesh |
—
|
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: red flesh instead of white flesh | Statement: [Pinot Teinturier, distinctionFromOtherPinots, red flesh instead of white flesh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distinctionFromOtherPinots Context triple: [Pinot Teinturier, distinctionFromOtherPinots, red flesh instead of white flesh]
-
A.
wineStyleComparedTo
Indicates a comparison between wines in terms of their style or stylistic characteristics.
-
B.
viticulturalCharacteristic
Indicates a relationship where a specific trait, quality, or property is attributed to viticulture or grape-growing practices.
-
C.
positionInCôteDeBeaune
Indicates that something is located within or belongs to the Côte de Beaune subregion.
-
D.
typicalViognierPercentage
Indicates the usual proportion of Viognier used within a given wine, blend, or production context.
-
E.
primaryGrapeVariety
Indicates that one entity is the main or predominant grape variety used in producing the other entity (typically a wine or wine-based product).
- 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_69c69f3567008190ab01d2ca7b53584a |
completed | March 27, 2026, 3:16 p.m. |
| NER | Named-entity recognition | batch_69c6fa1de8a4819091f9e9347835ce16 |
completed | March 27, 2026, 9:43 p.m. |
| PD | Predicate disambiguation | batch_69c6f4e485f88190910b39da52a955fe |
completed | March 27, 2026, 9:21 p.m. |
| PDg | Predicate description generation | batch_69c6f8195e5c8190835e28d44e19f6ef |
completed | March 27, 2026, 9:35 p.m. |
Created at: March 27, 2026, 3:54 p.m.