Triple
T17424158
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Route nationale 20 |
E423693
|
entity |
| Predicate | passesThroughCity |
P416
|
FINISHED |
| Object | Ax-les-Thermes |
—
|
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: Ax-les-Thermes | Statement: [Route nationale 20, passesThroughCity, Ax-les-Thermes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ax-les-Thermes Context triple: [Route nationale 20, passesThroughCity, Ax-les-Thermes]
-
A.
Ax-les-Thermes
chosen
Ax-les-Thermes is a spa and ski resort town in the French Pyrenees known for its thermal springs and mountain tourism.
-
B.
Ussat-les-Bains
Ussat-les-Bains is a spa village in the Ariège department of southwestern France, known for its thermal baths and proximity to notable caves in the Pyrenees.
-
C.
Monthermé
Monthermé is a commune in northeastern France’s Ardennes department, known for its scenic setting at the confluence of forested valleys and winding rivers.
-
D.
Saulx-les-Chartreux
Saulx-les-Chartreux is a commune in the Essonne department in the Île-de-France region of northern France.
-
E.
Évaux-les-Bains
Évaux-les-Bains is a French spa town in the Creuse department of central France, known for its thermal baths and historic architecture.
- 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_69d889d88b6081908bada047f5b3ba51 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4423999ac81909fdbd8bcffcb30c9 |
completed | April 19, 2026, 2:47 a.m. |
Created at: April 10, 2026, 5:46 a.m.