Triple
T10896922
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gouet |
E257333
|
entity |
| Predicate | alsoKnownAs |
P39
|
FINISHED |
| Object | Gouais Blanc |
E48344
|
NE 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: Gouais Blanc | Statement: [Gouet, alsoKnownAs, Gouais Blanc]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gouais Blanc Context triple: [Gouet, alsoKnownAs, Gouais Blanc]
-
A.
Gouais Blanc
chosen
Gouais Blanc is an ancient white wine grape variety historically important as a parent of many classic European grapes, including Chardonnay.
-
B.
Baco Blanc
Baco Blanc is a French hybrid white grape variety traditionally used in the production of Armagnac brandy.
-
C.
Ugni Blanc
Ugni Blanc is a widely planted white grape variety in France, best known for its high acidity and use in producing Cognac, Armagnac, and crisp, light still wines.
-
D.
Aligoté
Aligoté is a white grape variety from Burgundy known for producing light, crisp, and high-acid wines often enjoyed young.
-
E.
Vidal blanc
Vidal blanc is a hardy white hybrid wine grape, widely used in cool-climate regions to produce aromatic, often off-dry to sweet wines and ice wines.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6aa8550c8819095508a2ed9acf3db |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d75d02e4c88190b8286078e90bf913 |
completed | April 9, 2026, 8:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e15519e620819090e492861de6a567 |
completed | April 16, 2026, 9:31 p.m. |
Created at: April 8, 2026, 9:21 p.m.