Triple
T18672013
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Smallbridge |
E456500
|
entity |
| Predicate | nearbySettlement |
P350
|
FINISHED |
| Object | Wardle |
—
|
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: Wardle | Statement: [Smallbridge, nearbySettlement, Wardle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wardle Context triple: [Smallbridge, nearbySettlement, Wardle]
-
A.
Wardle
chosen
Wardle is a village in Greater Manchester, England, known for its moorland surroundings and historic textile industry roots.
-
B.
Downend
Downend is a suburban residential area on the northeastern edge of Bristol, within the unitary authority of South Gloucestershire in southwest England.
-
C.
Worle
Worle is a suburban area near Weston-super-Mare in North Somerset, England, known primarily as a residential community with rail links to surrounding regions.
-
D.
Holywell
Holywell is a historic market town in northeast Wales renowned for St Winefride's Well, a major medieval pilgrimage site often called the "Lourdes of Wales."
-
E.
Holywell
Holywell is a village in the Metropolitan Borough of North Tyneside in Tyne and Wear, England.
- 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_69d8d38f72b4819090a935175d9ca8af |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e556b21d2481908e1b8b583bfabb72 |
completed | April 19, 2026, 10:26 p.m. |
Created at: April 10, 2026, 11:48 a.m.