Triple
T16173572
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Le Puy route |
E392503
|
entity |
| Predicate | startsAt |
P12530
|
FINISHED |
| Object | Le Puy-en-Velay |
E57445
|
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: Le Puy-en-Velay | Statement: [Le Puy route, startsAt, Le Puy-en-Velay]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Le Puy-en-Velay Context triple: [Le Puy route, startsAt, Le Puy-en-Velay]
-
A.
Le Puy-en-Velay
chosen
Le Puy-en-Velay is a historic town in south-central France renowned for its volcanic landscape, Marian pilgrimage site, and traditional lace-making.
-
B.
Le Puy
Le Puy is a historic town in south-central France, renowned for its volcanic landscape, medieval architecture, and role as a major starting point on the pilgrimage route to Santiago de Compostela.
-
C.
Puy-Guillaume
Puy-Guillaume is a small commune in central France’s Puy-de-Dôme department, known for its rural character and location near the Dore River.
-
D.
Mont-Dore
Mont-Dore is a spa and ski resort town in central France’s Massif Central, known for its thermal springs and access to the nearby volcanic landscapes.
-
E.
Mont-Dore
Mont-Dore is a coastal commune and suburb of Nouméa in New Caledonia, known for its mountainous landscapes and residential areas.
- 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_69d87f1d32208190942e4e499a80c18c |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e21eb9b8208190b60874cec7a3a98e |
completed | April 17, 2026, 11:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a000ecd897c81908cbea306c9f95da3 |
completed | May 10, 2026, 4:51 a.m. |
Created at: April 10, 2026, 5:02 a.m.