Triple
T11089116
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mâcon AOC |
E262201
|
entity |
| Predicate | grapeRequirementWhite |
P91947
|
FINISHED |
| Object | Chardonnay must dominate 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: Chardonnay must dominate white wines | Statement: [Mâcon AOC, grapeRequirementWhite, Chardonnay must dominate white wines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: grapeRequirementWhite Context triple: [Mâcon AOC, grapeRequirementWhite, Chardonnay must dominate white wines]
-
A.
grapeCondition
Indicates the state or quality of a grape, such as its health, ripeness, or any notable physical condition.
-
B.
grapeVarietyAllowed
Indicates that a specific grape variety is permitted or authorized for use in a given context, such as a wine, region, or product specification.
-
C.
grapeMinimum
Indicates the minimum quantity, size, or threshold value associated with grapes in a given context.
-
D.
whiteWineProductionAllowed
Indicates that producing white wine is permitted under the relevant rules, regulations, or conditions.
-
E.
dominantGrapePercentageRequirement
chosen
Indicates the minimum percentage of a single grape variety that must be present in a wine for it to be considered dominant or to meet a specific labeling or classification rule.
- 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_69d6aa9a40d88190a373e2c7e48285db |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d799e844b08190987c7c8e8d626510 |
completed | April 9, 2026, 12:22 p.m. |
| PD | Predicate disambiguation | batch_69d744185a5881909ba4cf151d1798ec |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:27 p.m.