Triple
T23228770
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Millhouses |
E581089
|
entity |
| Predicate | traversedBy |
P225
|
FINISHED |
| Object | River Sheaf |
—
|
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 Sheaf | Statement: [Millhouses, traversedBy, River Sheaf]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: River Sheaf Context triple: [Millhouses, traversedBy, River Sheaf]
-
A.
River Sheaf
chosen
River Sheaf is a small urban river in South Yorkshire, England, that flows through Sheffield and gives the city its name.
-
B.
Teviot River
The Teviot River is a waterway in New Zealand’s South Island that flows through rural Otago before joining the larger Clutha River.
-
C.
River Leith
River Leith is a watercourse in Edinburgh, Scotland, that flows through the city to the historic Port of Leith on the Firth of Forth.
-
D.
River Tweed
River Tweed is a major river in the Scottish Borders and northern England, famed for its salmon fishing and as the namesake of tweed fabric.
-
E.
River Teviot
River Teviot is a major river in the Scottish Borders, known for flowing through Hawick and contributing significantly to the River Tweed catchment.
- 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_69e246043c48819089bae72c9a9c306c |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f192302e508190b286c284a261f172 |
completed | April 29, 2026, 5:08 a.m. |
Created at: April 17, 2026, 4:09 p.m.