Triple
T17850170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | École royale militaire de Sorèze |
E445778
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Sorèze |
—
|
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: Sorèze | Statement: [École royale militaire de Sorèze, locatedIn, Sorèze]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sorèze Context triple: [École royale militaire de Sorèze, locatedIn, Sorèze]
-
A.
Sorèze
chosen
Sorèze is a historic village in southern France known for its former royal military school and its picturesque setting near the Montagne Noire and the Canal du Midi’s water supply works.
-
B.
Reyssouze
Reyssouze is a river in eastern France that flows through the Ain department and the town of Bourg-en-Bresse.
-
C.
Bédarieux
Bédarieux is a commune in southern France’s Hérault department, known for its location in the Orb valley at the foothills of the Massif Central.
-
D.
Aiguèze
Aiguèze is a picturesque medieval village in southern France, known for its hilltop setting overlooking the Ardèche River and its well-preserved historic architecture.
-
E.
Laumière
Laumière is a Paris Métro station on the city’s northeastern side, located in the 19th arrondissement near the Canal de l’Ourcq.
- 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_69d8b9f26f18819089c9e43250bee6ae |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48ffe415c8190aed351c52b78a143 |
completed | April 19, 2026, 8:19 a.m. |
Created at: April 10, 2026, 10:16 a.m.