Triple
T4743315
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Glossop |
E105298
|
entity |
| Predicate | hasRiver |
P165
|
FINISHED |
| Object | River Etherow |
E444980
|
NE FINISHED |
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 Etherow | Statement: [Glossop, hasRiver, River Etherow]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: River Etherow Context triple: [Glossop, hasRiver, River Etherow]
-
A.
River Etherow
chosen
River Etherow is a river in north-west England that flows through the Longdendale valley, forming part of the boundary between Greater Manchester and Derbyshire.
-
B.
River Farset
The River Farset is a small river in Belfast, Northern Ireland, historically significant as the waterway beside which the city first developed.
-
C.
River Croal
River Croal is a small river in Greater Manchester, England, that flows through Bolton before joining the River Irwell.
-
D.
River Brock
River Brock is a small river in Lancashire, England, known for flowing through the Forest of Bowland before joining the River Wyre.
-
E.
River Gaywood
River Gaywood is a small river in Norfolk, England, that flows through the town of King’s Lynn before joining the Great Ouse.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69bd43ef87a48190a5bc3600711aa032 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd64a85e9c81908e9c7bbbb998953e |
completed | March 20, 2026, 3:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be4d851fcc8190bb7ae007f8a5ce1d |
completed | March 21, 2026, 7:49 a.m. |
Created at: March 20, 2026, 1:19 p.m.