Triple
T3482949
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Troyes |
E73536
|
entity |
| Predicate | historicalRegion |
P915
|
FINISHED |
| Object | Champagne |
E9584
|
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: Champagne | Statement: [Troyes, historicalRegion, Champagne]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Champagne Context triple: [Troyes, historicalRegion, Champagne]
-
A.
Champagne
chosen
Champagne is a renowned wine-producing region in northeastern France famous for its sparkling wines made primarily from Chardonnay, Pinot Noir, and Pinot Meunier grapes.
-
B.
blanc de blancs Champagne
Blanc de blancs Champagne is a sparkling wine made exclusively from white grapes, typically Chardonnay, prized for its elegance, finesse, and bright acidity.
-
C.
Dom Pérignon
Dom Pérignon is a prestigious vintage Champagne brand from Moët & Chandon, renowned worldwide as a symbol of luxury and fine French sparkling wine.
-
D.
Crémant de Loire sparkling wine
Crémant de Loire sparkling wine is a traditional-method French sparkling wine known for its crisp, elegant character and produced under strict quality regulations in the Loire Valley.
-
E.
Champenois
Champenois is a Romance regional language historically spoken in parts of northeastern France and adjacent areas of Wallonia in Belgium.
- 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_69ad85b3c9b08190857cae74c7f36da9 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adbb781e9c8190810fdd814f506127 |
completed | March 8, 2026, 6:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b3681e88d881908a2eeb93aa56d889 |
completed | March 13, 2026, 1:27 a.m. |
Created at: March 8, 2026, 3:17 p.m.