Triple
T19463725
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ornans |
E486939
|
entity |
| Predicate | river |
P165
|
FINISHED |
| Object | Loue |
—
|
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: Loue | Statement: [Ornans, river, Loue]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Loue Context triple: [Ornans, river, Loue]
-
A.
Loue
chosen
The Loue is a river in eastern France, known for its scenic valleys and as a tributary of the Doubs in the Bourgogne-Franche-Comté region.
-
B.
Louvois
Louvois was a powerful French statesman, best known as Louis XIV’s influential war minister who significantly shaped France’s military administration in the late 17th century.
-
C.
Rive-de-Gier
Rive-de-Gier is a commune in central France’s Loire department, historically known for its coal mining and glassmaking industries.
-
D.
Portovesme
Portovesme is a small port and industrial locality on the southwestern coast of Sardinia, Italy, serving as a maritime hub for regional ferry and cargo traffic.
-
E.
Villeblevin
Villeblevin is a small commune in north-central France, best known as the place where writer Albert Camus died in a car accident.
- 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_69d8e8d86d608190bd199a98d0297f27 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e633cf95988190b13b2153e67d0cac |
completed | April 20, 2026, 2:10 p.m. |
Created at: April 10, 2026, 1:38 p.m.