Triple
T20876647
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Breadalbane |
E514032
|
entity |
| Predicate | hasRiver |
P165
|
FINISHED |
| Object | River Lyon |
—
|
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 Lyon | Statement: [Breadalbane, hasRiver, River Lyon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: River Lyon Context triple: [Breadalbane, hasRiver, River Lyon]
-
A.
River Lyon
chosen
The River Lyon is a scenic river in the Scottish Highlands that flows through Glen Lyon before joining the River Tay.
-
B.
Nive River
The Nive River is a waterway in southwestern France that flows through the Basque Country and joins the Adour River at Bayonne before reaching the Atlantic coast.
-
C.
River Divie
River Divie is a small river in northeast Scotland that flows through Moray before joining the River Findhorn.
-
D.
La Doua
La Doua is a major university and research campus area in the Lyon metropolitan region, known for hosting several science and engineering institutions.
-
E.
Breg River
The Breg River is a headstream of the Danube in Germany’s Black Forest, known as one of the two main source rivers that form the Danube.
- 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_69e0b4f733f081908a401c0b7beb0b9f |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c6767ec0819080721e2e75bd0d66 |
completed | April 21, 2026, 12:36 a.m. |
Created at: April 16, 2026, 12:45 p.m.