Triple
T16995320
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Traeth yr Afon |
E412298
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | River Ogmore |
—
|
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 Ogmore | Statement: [Traeth yr Afon, adjacentTo, River Ogmore]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: River Ogmore Context triple: [Traeth yr Afon, adjacentTo, River Ogmore]
-
A.
River Ogmore
chosen
River Ogmore is a river in South Wales that flows through the town of Bridgend before reaching the Bristol Channel.
-
B.
River Kinder
The River Kinder is a small moorland river in the Peak District of England, known for its dramatic Kinder Downfall waterfall and rugged upland scenery.
-
C.
River Og
The River Og is a small tributary watercourse in Wiltshire, England, that feeds into the River Kennet.
-
D.
River Brun
River Brun is a small river in Lancashire, England, that flows through the town of Burnley and contributes to its local landscape and waterways.
-
E.
Orbieu River
The Orbieu River is a watercourse in southern France that flows through the Aude department and joins the Aude River.
- 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_69d886cb581c8190ab05f4b429c9cd85 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d2879af081909665f9f838bcfbe7 |
completed | April 18, 2026, 6:50 p.m. |
Created at: April 10, 2026, 5:32 a.m.