Triple
T11140261
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St Peter’s Church, Upwell |
E263529
|
entity |
| Predicate | parish |
P2739
|
FINISHED |
| Object | Upwell |
E48862
|
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: Upwell | Statement: [St Peter’s Church, Upwell, parish, Upwell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Upwell Context triple: [St Peter’s Church, Upwell, parish, Upwell]
-
A.
Upwell
chosen
Upwell is a rural village and civil parish in Norfolk, England, known for its historic churches and waterways near the Cambridgeshire border.
-
B.
Tripwell
Tripwell is a small settlement on the island of Whalsay in the Shetland archipelago of Scotland.
-
C.
The WELL
The WELL is a major fitness, recreation, and wellness center serving students and the campus community at California State University, Sacramento.
-
D.
Purewell
Purewell is a residential suburb and local area forming part of the town of Christchurch in Dorset, England.
-
E.
Clearpoint
Clearpoint is a popular line of Paper Mate mechanical pencils known for their side-click advance mechanism and comfortable, ergonomic design.
- 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_69d6aa9c0ba08190bbd19c217489b755 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e860ca408190bea461e115f04fd7 |
completed | April 9, 2026, 5:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e463177bfc81908a3e66ffc0777777 |
completed | April 19, 2026, 5:07 a.m. |
Created at: April 8, 2026, 9:28 p.m.