Triple
T2582318
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ain |
E57120
|
entity |
| Predicate | hasRegion |
P285
|
FINISHED |
| Object | Bresse |
E160069
|
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: Bresse | Statement: [Ain, hasRegion, Bresse]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bresse Context triple: [Ain, hasRegion, Bresse]
-
A.
Bresse
chosen
Bresse is a historical region in eastern France known for its rich agricultural land, distinctive culinary traditions, and cultural ties to the Franco-Provençal linguistic area.
-
B.
Brioude
Brioude is a historic town in south-central France known for its Romanesque Basilica of Saint-Julien and its location in the Haute-Loire department of the Auvergne region.
-
C.
Tournus
Tournus is a historic town in eastern France’s Burgundy region, known for its Romanesque abbey and riverside setting along the Saône.
-
D.
Beaune
Beaune is a historic town in eastern France renowned as the wine capital of Burgundy and a center of Burgundy’s prestigious vineyards and wine trade.
-
E.
Mâconnais
Mâconnais is a wine-producing subregion in southern Burgundy, France, best known for its Chardonnay-based white 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_69ab4a4dca6481908c301f8e317396e7 |
completed | March 6, 2026, 9:42 p.m. |
| NER | Named-entity recognition | batch_69abd3c843bc8190837cea3441bf3ca1 |
completed | March 7, 2026, 7:29 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b2e803e994819085dae09224fae2a3 |
completed | March 12, 2026, 4:21 p.m. |
Created at: March 6, 2026, 9:49 p.m.