Triple
T9701589
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heytesbury |
E234788
|
entity |
| Predicate | locatedOn |
P40
|
FINISHED |
| Object | River Wylye |
E343495
|
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 Wylye | Statement: [Heytesbury, locatedOn, River Wylye]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: River Wylye Context triple: [Heytesbury, locatedOn, River Wylye]
-
A.
River Wylye
chosen
River Wylye is a chalk stream in Wiltshire, England, known for its clear waters, rich wildlife, and popularity for fly fishing.
-
B.
River Ancholme
The River Ancholme is a river in Lincolnshire, England, that flows north through the county’s agricultural lowlands before joining the Humber Estuary.
-
C.
River Wick
River Wick is a small river in northern Scotland that flows through the town of Wick before entering the North Sea.
-
D.
River Stort
The River Stort is a tributary river in southern England that flows through Hertfordshire and Essex, joining the River Lea near the town of Hoddesdon.
-
E.
River Lyde
The River Lyde is a small river in Hampshire, England, that flows through rural landscapes before joining the River Loddon.
- 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_69ca84cc78808190a56f3402b7c139a7 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9d70f55c8190934f37c25e9d4ba4 |
completed | April 1, 2026, 10:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d29999e9248190b2f1900fa7ad3da5 |
completed | April 5, 2026, 5:19 p.m. |
Created at: March 30, 2026, 8:18 p.m.