Triple
T26946349
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Domaine de la Romanée-Conti |
E678653
|
entity |
| Predicate | primaryGrapeForWhites |
P975
|
FINISHED |
| Object | 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: Chardonnay | Statement: [Domaine de la Romanée-Conti, primaryGrapeForWhites, Chardonnay]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryGrapeForWhites Context triple: [Domaine de la Romanée-Conti, primaryGrapeForWhites, Chardonnay]
-
A.
primaryGrapeVariety
chosen
Indicates that one entity is the main or predominant grape variety used in producing the other entity (typically a wine or wine-based product).
-
B.
primaryGrapeFamily
Indicates that one grape variety belongs to, or is classified under, a broader primary grape family.
-
C.
primaryGrapeUse
Indicates that a grape variety is primarily used for a particular purpose, such as winemaking, table consumption, or raisin production.
-
D.
whiteWineFrom
Indicates that one entity is a white wine that originates from, or is produced in, the region or source specified by the other entity.
-
E.
grapeRole_SauvignonBlanc
Indicates that the role or function being referred to is specifically associated with Sauvignon Blanc grapes.
- 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_69eeeb4d69588190a7c912164a1c37b3 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69fedec693b08190b0f8bfdb921e0766 |
completed | May 9, 2026, 7:14 a.m. |
| PD | Predicate disambiguation | batch_69fede16c1d48190a20d8a9c5722c307 |
completed | May 9, 2026, 7:11 a.m. |
Created at: April 27, 2026, 6:21 a.m.