Triple
T11010089
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gamay for red and rosé wines |
E260222
|
entity |
| Predicate | vinificationTechniqueOftenUsed |
P77755
|
FINISHED |
| Object | carbonic maceration |
—
|
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: carbonic maceration | Statement: [Gamay for red and rosé wines, vinificationTechniqueOftenUsed, carbonic maceration]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: vinificationTechniqueOftenUsed Context triple: [Gamay for red and rosé wines, vinificationTechniqueOftenUsed, carbonic maceration]
-
A.
vinificationUse
chosen
Indicates the process or method of winemaking applied to a given wine or batch.
-
B.
commonVinification
Indicates that two wines share the same or very similar vinification (winemaking) process.
-
C.
vinification
Indicates the process by which grapes (or other fruits) are transformed into wine through fermentation and related winemaking steps.
-
D.
commonVinificationGoal
Indicates that two or more vinification processes share the same intended winemaking objective or outcome.
-
E.
traditionalVinification
Indicates that a wine is produced using traditional or historically established winemaking methods rather than modern or industrial techniques.
- 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_69d6aa9687448190b28d353b1b6a610e |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d79788d44c819084f35693ed96f422 |
completed | April 9, 2026, 12:11 p.m. |
| PD | Predicate disambiguation | batch_69d72e96be6c8190a46c69f61b2d8cd4 |
completed | April 9, 2026, 4:44 a.m. |
Created at: April 8, 2026, 9:25 p.m.