Triple
T6626502
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Darlington |
E149816
|
entity |
| Predicate | hasRiver |
P165
|
FINISHED |
| Object | River Skerne |
E611315
|
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 Skerne | Statement: [Darlington, hasRiver, River Skerne]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: River Skerne Context triple: [Darlington, hasRiver, River Skerne]
-
A.
River Skerne
chosen
River Skerne is a small river in County Durham, England, that flows through Darlington before joining the River Tees.
-
B.
River Colne
The River Colne is a watercourse in West Yorkshire, England, flowing through Huddersfield and the Colne Valley before joining the River Calder.
-
C.
River Colne
The River Colne is a tributary river in southern England that flows through Hertfordshire and Buckinghamshire before joining the River Thames near Staines.
-
D.
River Colne
The River Colne is a river in southeast England that flows through Essex, including the town of Colchester, before reaching the North Sea.
-
E.
River Swale
The River Swale is a fast-flowing river in North Yorkshire, England, known for running through Swaledale in the Yorkshire Dales and for its scenic valleys and frequent flooding.
- 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_69c687ee50048190aa151765bef16193 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6afa0feb0819099629c0fba590a05 |
completed | March 27, 2026, 4:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c70ae8248081909a0f6628583f4626 |
completed | March 27, 2026, 10:55 p.m. |
Created at: March 27, 2026, 1:58 p.m.