Triple
T22761769
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dulverton |
E563008
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | River Exe |
—
|
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 Exe | Statement: [Dulverton, near, River Exe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: River Exe Context triple: [Dulverton, near, River Exe]
-
A.
River Exe
chosen
The River Exe is a major river in Devon, England, flowing from Exmoor to the English Channel at Exmouth and shaping the landscapes and settlements along its estuary.
-
B.
River Looe
River Looe is a short coastal river in Cornwall, England, that flows through the town of Looe before reaching the English Channel.
-
C.
River Devon
River Devon is a small river in central Scotland that flows through Clackmannanshire before joining the River Forth.
-
D.
River Devon
The River Devon is a river in central England that flows through Leicestershire and Nottinghamshire before joining the River Trent.
-
E.
River Torridge
River Torridge is a river in north Devon, England, known for flowing through towns like Great Torrington and Bideford before reaching the Bristol Channel.
- 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_69e24552e11c81909c2d61578a558bd7 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17a7d09ac8190b773e8977cb8a829 |
completed | April 29, 2026, 3:26 a.m. |
Created at: April 17, 2026, 3:26 p.m.