Triple
T15353386
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Provence wine region |
E367109
|
entity |
| Predicate | hasSubregion |
P285
|
FINISHED |
| Object | Bandol |
E401920
|
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: Bandol | Statement: [Provence wine region, hasSubregion, Bandol]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bandol Context triple: [Provence wine region, hasSubregion, Bandol]
-
A.
Bandol
chosen
Bandol is a renowned coastal town and wine appellation in southeastern France, famous for its robust Mourvèdre-based rosé and red wines.
-
B.
Bayona
Bayona is a Spanish surname most notably associated with filmmaker J. A. Bayona, known for directing acclaimed films such as "The Orphanage" and "The Impossible."
-
C.
Bordeira
Bordeira is a civil parish in the municipality of Aljezur in Portugal’s Algarve region, known for its rugged Atlantic coastline and scenic beaches.
-
D.
Moncalvo
Moncalvo is a small historic town in Italy’s Piedmont region, known as one of the country’s smallest cities and for its wine and truffle production.
-
E.
Baulmes
Baulmes is a Swiss village and municipality in the canton of Vaud, situated near the Jura Mountains and known for its scenic rural landscape.
- 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_69d85a1355608190a6673ddb67231d54 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e2a8e88819093e4b7479b2c80cd |
completed | April 16, 2026, 1:40 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff01ff42d48190897e6653d2b4f8a4 |
completed | May 9, 2026, 9:44 a.m. |
Created at: April 10, 2026, 3:18 a.m.