Triple
T23453270
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Doubs |
E567843
|
entity |
| Predicate | bordersDepartment |
P224
|
FINISHED |
| Object | Haute-Saône |
—
|
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: Haute-Saône | Statement: [Doubs, bordersDepartment, Haute-Saône]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Haute-Saône Context triple: [Doubs, bordersDepartment, Haute-Saône]
-
A.
Haute-Saône
chosen
Haute-Saône is a rural department in the Bourgogne-Franche-Comté region of eastern France, known for its forests, rivers, and historic villages.
-
B.
Haut-Doubs
Haut-Doubs is a mountainous area in eastern France’s Doubs department, known for its Jura landscapes, traditional cheese production, and proximity to the Swiss border.
-
C.
Haute-Marne
Haute-Marne is a rural department in northeastern France known for its forests, rivers, and historic towns such as Chaumont and Langres.
-
D.
Pays de Montbéliard
Pays de Montbéliard is a historical and industrial area in eastern France centered on the town of Montbéliard, known for its automotive industry and cultural ties to nearby Switzerland and Germany.
-
E.
Drôme
Drôme is a department in southeastern France known for its diverse landscapes, historic towns, and location between the Alps and the Rhône Valley.
- 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_69e2458b4c888190b1d7998f9862a558 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f1a694f19081909117bc9b10ca8a83 |
completed | April 29, 2026, 6:35 a.m. |
Created at: April 17, 2026, 5:52 p.m.