Triple
T13590829
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dom Pérignon |
E324686
|
entity |
| Predicate | baseWineBlend |
P103849
|
FINISHED |
| Object | Chardonnay and Pinot Noir blend |
—
|
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: Chardonnay and Pinot Noir blend | Statement: [Dom Pérignon, baseWineBlend, Chardonnay and Pinot Noir blend]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: baseWineBlend Context triple: [Dom Pérignon, baseWineBlend, Chardonnay and Pinot Noir blend]
-
A.
typicalBlendCabernetFrancPercentage
Indicates the percentage of Cabernet Franc that is typically included in a particular wine blend.
-
B.
wineBlendRole
Indicates the specific role or function that a wine plays within a blend (e.g., primary component, supporting component, or minor addition).
-
C.
typicalBlendMerlotPercentage
Indicates the usual proportion of Merlot used in a blend relative to the other grape varieties.
-
D.
grapeBlendPartner
chosen
Indicates that two grape varieties are commonly combined or well-suited to be blended together in winemaking.
-
E.
wineVariety
Indicates the specific type or variety of wine associated with 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_69d80769eaf081909d82f44e484d6113 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbb056ce088190a6feb4266633d18b |
completed | April 12, 2026, 2:46 p.m. |
| PD | Predicate disambiguation | batch_69dbae18eaf48190809e8b365856cde9 |
completed | April 12, 2026, 2:37 p.m. |
Created at: April 9, 2026, 9:49 p.m.