Triple
T5368236
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vallée de Montjoie |
E108780
|
entity |
| Predicate | mainRiver |
P165
|
FINISHED |
| Object | Bon Nant |
E296413
|
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: Bon Nant | Statement: [Vallée de Montjoie, mainRiver, Bon Nant]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bon Nant Context triple: [Vallée de Montjoie, mainRiver, Bon Nant]
-
A.
Bon Nant
chosen
Bon Nant is a mountain stream in the French Alps that flows through the Montjoie Valley before joining the Arve River.
-
B.
Marly Forest
Marly Forest is a historic woodland area in the Yvelines department of north-central France, known for its natural landscapes and former royal hunting grounds.
-
C.
Gros Caillou
Gros Caillou is a famous large glacial erratic stone and emblematic monument of Lyon, France, symbolizing the La Croix-Rousse district.
-
D.
Butte du Lion
Butte du Lion is a large conical memorial mound in Waterloo, Belgium, topped by a cast-iron lion statue commemorating the Battle of Waterloo.
-
E.
La Pine
La Pine is a small rural city in Deschutes County known as a gateway to outdoor recreation in Central Oregon’s forests, rivers, and high desert.
- 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_69bd440c77948190aad2a5f39b7b80f5 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd86856f688190a34ab93619bae134 |
completed | March 20, 2026, 5:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf2928859881908ac238feca132d07 |
completed | March 21, 2026, 11:26 p.m. |
Created at: March 20, 2026, 2:02 p.m.