Triple
T22348750
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dora Baltea |
E552469
|
entity |
| Predicate | hasTributary |
P415
|
FINISHED |
| Object | Dora di Veny |
—
|
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: Dora di Veny | Statement: [Dora Baltea, hasTributary, Dora di Veny]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dora di Veny Context triple: [Dora Baltea, hasTributary, Dora di Veny]
-
A.
Dora di Veny
chosen
Dora di Veny is a mountain stream in Italy’s Aosta Valley that drains the southern side of Mont Blanc and contributes to the upper course of the Dora Baltea river.
-
B.
Dora di Valgrisenche
Dora di Valgrisenche is a mountain stream in Italy’s Aosta Valley that drains the Valgrisenche valley and feeds into the Dora Baltea river system.
-
C.
Dora di Valsavarenche
Dora di Valsavarenche is a mountain stream in Italy’s Aosta Valley that drains the Valsavarenche valley and feeds into the Dora Baltea river system.
-
D.
Léonie
Léonie is a feminine given name of French origin, derived from the Latin "Leo" meaning "lion."
-
E.
Margeride
Margeride is a mountainous and sparsely populated region in south-central France known for its granite plateaus, forests, and traditional rural landscapes.
- 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_69e11e4a0ad08190a385b4d343cf6524 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1579a1c308190ae2174f99ae317ab |
completed | April 29, 2026, 12:58 a.m. |
Created at: April 16, 2026, 8:43 p.m.