Triple
T3827427
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marvejols |
E88723
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Aubrac |
E61549
|
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: Aubrac | Statement: [Marvejols, near, Aubrac]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aubrac Context triple: [Marvejols, near, Aubrac]
-
A.
Cévennes
The Cévennes is a rugged mountainous region in south-central France known for its dramatic landscapes, chestnut forests, and historical role as a refuge for Protestant Huguenots.
-
B.
Grands Causses
chosen
Grands Causses is a rugged limestone plateau region in southern France known for its deep gorges, dramatic cliffs, and pastoral landscapes within the broader Massif Central.
-
C.
Morvan Massif
The Morvan Massif is a heavily forested highland region in central France known for its rounded granite hills, lakes, and protected natural landscapes.
-
D.
Luberon massif
The Luberon massif is a picturesque mountain range in southeastern France known for its hilltop villages, lavender fields, and protected natural landscapes within the Luberon Regional Nature Park.
-
E.
Fléron
Fléron is a municipality in eastern Belgium located in the Walloon region’s Province of Liège.
- 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_69aed9538cf881909d9ce8ca4ac7c18c |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeeb66c0bc819084d9a9fe32e8433a |
completed | March 9, 2026, 3:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b503f9df8c8190b42c544e827d6c76 |
completed | March 14, 2026, 6:45 a.m. |
Created at: March 9, 2026, 3:17 p.m.