Triple
T19007130
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ussel railway station |
E465116
|
entity |
| Predicate | serves |
P98
|
FINISHED |
| Object | Ussel |
—
|
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: Ussel | Statement: [Ussel railway station, serves, Ussel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ussel Context triple: [Ussel railway station, serves, Ussel]
-
A.
Ussel
chosen
Ussel is a small commune in central France known as a local administrative and service center in the Corrèze department of the Nouvelle-Aquitaine region.
-
B.
Étupes
Étupes is a small commune in eastern France’s Bourgogne-Franche-Comté region, near the city of Montbéliard.
-
C.
Aurillac
Aurillac is a historic town in south-central France, known as the capital of the Cantal department and for its traditional umbrella-making industry.
-
D.
Cauterets
Cauterets is a spa and ski resort town in the French Pyrenees known for its thermal baths, mountain scenery, and access to popular hiking areas.
-
E.
Vièze
Vièze is a river in the canton of Valais in southwestern Switzerland that flows through the town of Monthey before joining the Rhône.
- 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_69d8dd01a56c81909694a128c66b21d7 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d6a561848190bd957f248471c191 |
completed | April 20, 2026, 7:32 a.m. |
Created at: April 10, 2026, 12:01 p.m.