Triple
T10943960
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lac du Bourget |
E258545
|
entity |
| Predicate | nearMountain |
P31783
|
FINISHED |
| Object | Mont Revard |
E271524
|
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: Mont Revard | Statement: [Lac du Bourget, nearMountain, Mont Revard]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mont Revard Context triple: [Lac du Bourget, nearMountain, Mont Revard]
-
A.
Mont Revard
chosen
Mont Revard is a prominent mountain in the French Alps known for its panoramic views over Lake Bourget and its popularity for skiing, hiking, and cycling.
-
B.
Grand Veymont
Grand Veymont is a prominent mountain peak in the French Prealps, known for its panoramic views and popular hiking routes within the Vercors region.
-
C.
Roquebillière
Roquebillière is a small commune in southeastern France, situated in the Alpes-Maritimes department in the Provence-Alpes-Côte d’Azur region.
-
D.
Mont Dauban
Mont Dauban is the tallest mountain on Silhouette Island in the Seychelles, known for its lush tropical forests and panoramic views over the Indian Ocean.
-
E.
Larroquette
Larroquette is the surname of John Larroquette, an American actor best known for his Emmy-winning role as Dan Fielding on the sitcom "Night Court."
- 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_69d6aa8769b4819082bfe5e61b9017f0 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d770c4d59481908a5900fc8cf9ecc3 |
completed | April 9, 2026, 9:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e23c2dea008190af68336a096b7f7c |
completed | April 17, 2026, 1:57 p.m. |
Created at: April 8, 2026, 9:23 p.m.