Triple
T10687591
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Portland |
E251918
|
entity |
| Predicate | hasVillage |
P4011
|
FINISHED |
| Object | Southwell |
E153505
|
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: Southwell | Statement: [Portland, hasVillage, Southwell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Southwell Context triple: [Portland, hasVillage, Southwell]
-
A.
Southwell
chosen
Southwell is a small coastal settlement on the Isle of Portland in Dorset, England, known for its proximity to dramatic cliffs and quarrying heritage.
-
B.
Ketton
Ketton is a village and civil parish in Rutland, England, known for its historic limestone quarries and rural character.
-
C.
Wolsingham
Wolsingham is a small historic market town and civil parish in County Durham, England, situated in the rural valley of Weardale.
-
D.
Sancroft
Sancroft is an English surname most notably associated with William Sancroft, the 17th-century Archbishop of Canterbury.
-
E.
Southwell Minster
Southwell Minster is a historic Anglican cathedral in the town of Southwell, renowned for its Norman architecture and distinctive twin towers.
- 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_69d6aa5bd7c08190a816e733b4045c23 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6fd19f0f481909eeaa75d17d9c060 |
completed | April 9, 2026, 1:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d9889d1f988190938be54771161b00 |
completed | April 10, 2026, 11:32 p.m. |
Created at: April 8, 2026, 9:10 p.m.