Triple
T20838753
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint-Claude |
E513031
|
entity |
| Predicate | locatedOn |
P40
|
FINISHED |
| Object | river Bienne |
—
|
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: river Bienne | Statement: [Saint-Claude, locatedOn, river Bienne]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: river Bienne Context triple: [Saint-Claude, locatedOn, river Bienne]
-
A.
River Reuss
The River Reuss is a major Swiss river that flows from the Gotthard region through cities such as Lucerne before joining the Aare.
-
B.
Lütschine
The Lütschine is a river in the Bernese Oberland region of Switzerland, known for flowing through the Lauterbrunnen and Grindelwald valleys before joining the Aare near Interlaken.
-
C.
Bienne River
chosen
The Bienne River is a watercourse in eastern France that flows through the Jura region before joining the Ain River.
-
D.
river Sarine
The river Sarine is a major watercourse in western Switzerland that flows through the canton of Fribourg and lends its name to the surrounding Sarine district.
-
E.
Seerhein
Seerhein is a short stretch of the Rhine River connecting the Untersee and Obersee basins of Lake Constance along the Swiss-German border.
- 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_69e0b4cf62a88190bbf92351e9e57259 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c32928788190be8ca57923eefd7e |
completed | April 21, 2026, 12:22 a.m. |
Created at: April 16, 2026, 12:42 p.m.