Triple
T21261922
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Émile Chartier |
E524024
|
entity |
| Predicate | placeOfBirth |
P1
|
FINISHED |
| Object | Mortagne-au-Perche |
—
|
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: Mortagne-au-Perche | Statement: [Émile Chartier, placeOfBirth, Mortagne-au-Perche]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mortagne-au-Perche Context triple: [Émile Chartier, placeOfBirth, Mortagne-au-Perche]
-
A.
Mortagne-au-Perche
chosen
Mortagne-au-Perche is a historic market town in northwestern France known as the traditional capital of the Perche region.
-
B.
Mortagne-sur-Sèvre
Mortagne-sur-Sèvre is a commune in western France’s Vendée department, known for its scenic setting along the Sèvre Nantaise river and its historical heritage.
-
C.
Mortagnais
Mortagnais are the inhabitants or natives of the French commune of Mortagne-au-Perche in the Normandy region.
-
D.
Bellême
Bellême is a historic town in northwestern France’s Normandy region, known for its medieval architecture and picturesque setting on the edge of the Perche forest.
-
E.
Nancoury
Nancoury is an alternative name for the Nancowry language, an Austroasiatic language spoken in India’s Nicobar Islands.
- 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_69e0b5156d7881909bd4f83676590715 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e735e899e081909d3c98fb12a8b476 |
completed | April 21, 2026, 8:31 a.m. |
Created at: April 16, 2026, 3:59 p.m.