Triple
T21534956
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jura wines |
E531326
|
entity |
| Predicate | appellation |
P16569
|
FINISHED |
| Object | Arbois AOC |
—
|
NE NERFINISHED |
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: Arbois AOC | Statement: [Jura wines, appellation, Arbois AOC]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arbois AOC Context triple: [Jura wines, appellation, Arbois AOC]
-
A.
Arbois AOC
chosen
Arbois AOC is a French wine appellation in the Jura region, renowned for its distinctive red, white, and especially oxidative Vin Jaune wines.
-
B.
Montagny AOC
Montagny AOC is a French appellation in the Côte Chalonnaise of Burgundy known for producing dry white wines exclusively from Chardonnay grapes.
-
C.
Buzet AOC
Buzet AOC is a French wine appellation in the Sud-Ouest region known for its robust red blends and characterful whites produced along the Garonne River.
-
D.
Chiroubles AOC
Chiroubles AOC is a French appellation in the Beaujolais region known for producing light, fragrant red wines primarily from the Gamay grape.
-
E.
Ladoix AOC
Ladoix AOC is a French wine appellation in the Côte de Beaune subregion of Burgundy, known for producing both red Pinot Noir and white Chardonnay wines.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c45e5b8881908ac18fc2f493b114 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee9d0b9888819094e424d33c14d5d0 |
completed | April 26, 2026, 11:17 p.m. |
Created at: April 16, 2026, 6:27 p.m.