Triple
T12866856
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clayhanger |
E307741
|
entity |
| Predicate | setInFictionalTown |
P7550
|
FINISHED |
| Object | Bursley |
E628315
|
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: Bursley | Statement: [Clayhanger, setInFictionalTown, Bursley]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bursley Context triple: [Clayhanger, setInFictionalTown, Bursley]
-
A.
Bursley
chosen
Bursley is a fictional Staffordshire pottery town created by Arnold Bennett as one of his "Five Towns" and used as a principal setting in several of his novels.
-
B.
Bromsgrove
Bromsgrove is a market town and district in Worcestershire, England, known historically for its nail-making industry and later as a residential and commuter area.
-
C.
Yate
Yate is a town in South Gloucestershire, England, known as a residential and commercial centre north of Bristol.
-
D.
Rugeley
Rugeley is a market town in Staffordshire, England, historically known for its coal mining industry and location on the River Trent.
-
E.
Epsom
Epsom is a market town in Surrey, England, best known for the Epsom Downs Racecourse and the famous Epsom Derby horse race.
- 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_69d7bdf69bc48190af6c2621f28ca351 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9708e0b788190b72a3057e271c227 |
completed | April 10, 2026, 9:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f69bb092b88190b159f1d79156cf86 |
completed | May 3, 2026, 12:49 a.m. |
Created at: April 9, 2026, 5:38 p.m.