Triple
T16173585
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Le Puy route |
E392503
|
entity |
| Predicate | passesThrough |
P225
|
FINISHED |
| Object | Estaing |
E465710
|
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: Estaing | Statement: [Le Puy route, passesThrough, Estaing]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Estaing Context triple: [Le Puy route, passesThrough, Estaing]
-
A.
Estaing
chosen
Estaing is a historic village in the Aveyron department of southern France, known for its medieval architecture and picturesque setting along the Lot River.
-
B.
Marlais
Marlais is the distinctive middle name of Welsh poet and writer Dylan Thomas, reflecting his Welsh heritage.
-
C.
Fontenais
Fontenais is a municipality in the canton of Jura in northwestern Switzerland, situated in the Ajoie region near the town of Porrentruy.
-
D.
Ozanne
Ozanne is a river in France that serves as a right-bank tributary of the Loir.
-
E.
Sauvy
Sauvy is a French surname most notably borne by Alfred Sauvy, a prominent demographer, sociologist, and economist.
- 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_69fff7bfc3ac819082596cc533c5faa4 |
completed | May 10, 2026, 3:13 a.m. |
Created at: April 10, 2026, 5:02 a.m.