Triple
T697448
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Reginald Dyer |
E13922
|
entity |
| Predicate | placeOfDeath |
P21
|
FINISHED |
| Object | Long Ashton |
E69583
|
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: Long Ashton | Statement: [Reginald Dyer, placeOfDeath, Long Ashton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Long Ashton Context triple: [Reginald Dyer, placeOfDeath, Long Ashton]
-
A.
Long Ashton
chosen
Long Ashton is a village and civil parish in North Somerset, England, located just southwest of Bristol.
-
B.
Hordley
Hordley is a small rural settlement located in the parish of St. Thomas in the East, Jamaica.
-
C.
Royton
Royton is a town in Greater Manchester, England, historically part of Lancashire and now within the Metropolitan Borough of Oldham.
-
D.
Larkhill
Larkhill is a major British Army garrison on Salisbury Plain in Wiltshire, England, best known as a principal base and training area for the Royal Artillery.
-
E.
Ashton-under-Lyne
Ashton-under-Lyne is a market town in Tameside, Greater Manchester, England, known for its historic town centre and role as a local commercial and transport hub.
- 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_69a493406c408190957eeec9048a8fb6 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a0c8055881909565ebde2be8fd7a |
completed | March 1, 2026, 8:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a654dace34819094c74f7c6ff4716c |
completed | March 3, 2026, 3:26 a.m. |
Created at: March 1, 2026, 7:36 p.m.