Triple
T4255308
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Meldon Viaduct |
E95958
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Okehampton |
E95958
|
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: Okehampton | Statement: [Meldon Viaduct, locatedNear, Okehampton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Okehampton Context triple: [Meldon Viaduct, locatedNear, Okehampton]
-
A.
Okehampton
chosen
Okehampton is a historic market town in Devon, England, known for its medieval castle and role as a former parliamentary borough.
-
B.
Cinderford
Cinderford is a small industrial town in Gloucestershire, England, historically associated with coal mining and situated within the Forest of Dean.
-
C.
Bramshott
Bramshott is a historic village in Hampshire, England, known for its picturesque countryside and association with nearby heathland areas.
-
D.
Shrivenham
Shrivenham is a village in Oxfordshire, England, known for its historic high street, rural setting, and association with nearby military and academic institutions.
-
E.
Heytesbury
Heytesbury is a historic village and former parliamentary borough in Wiltshire, England.
- 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_69b3453f759881909b91f01a1e82c036 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34ec036e8819087d8585170707545 |
completed | March 12, 2026, 11:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5c7151108819082b2f37945d6139e |
completed | March 14, 2026, 8:37 p.m. |
Created at: March 12, 2026, 11:06 p.m.