Triple
T9324395
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bouzeron AOC |
E224349
|
entity |
| Predicate | mainGrapeShare |
P11949
|
FINISHED |
| Object | 100% Aligoté in white wines |
—
|
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: 100% Aligoté in white wines | Statement: [Bouzeron AOC, mainGrapeShare, 100% Aligoté in white wines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mainGrapeShare Context triple: [Bouzeron AOC, mainGrapeShare, 100% Aligoté in white wines]
-
A.
grapeSource
Indicates that one entity is the origin or provider of grapes used by another entity.
-
B.
sharesGrandCruVineyardsWith
Indicates that two entities share ownership, use, or association with the same Grand Cru–classified vineyards.
-
C.
usesGrapeType
chosen
Indicates that one entity employs or incorporates a specific type or variety of grape in its composition, production, or process.
-
D.
whiteWineShare
Indicates the proportion or share of white wine within a larger set, such as total wine consumption, production, or sales.
-
E.
grapeFamily
Indicates that one entity belongs to, or is classified within, the same botanical family as 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_69ca8426d48481909596360f7791c7dd |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd36f5c41c81908104c5b30e14827e |
completed | April 1, 2026, 3:17 p.m. |
| PD | Predicate disambiguation | batch_69cc7a643924819097f01144734901cf |
completed | April 1, 2026, 1:52 a.m. |
Created at: March 30, 2026, 7:38 p.m.