Triple
T20722080
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thornsett |
E509339
|
entity |
| Predicate | hasNearbySettlement |
P4647
|
FINISHED |
| Object | Hayfield |
—
|
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: Hayfield | Statement: [Thornsett, hasNearbySettlement, Hayfield]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hayfield Context triple: [Thornsett, hasNearbySettlement, Hayfield]
-
A.
Hayfield
chosen
Hayfield is a village in Derbyshire, England, known as a gateway to the Peak District and the moorland plateau of Kinder Scout.
-
B.
Homersfield
Homersfield is a small village and civil parish on the River Waveney in eastern England, known for its historic bridge and rural Suffolk setting.
-
C.
Blanefield
Blanefield is a small village in central Scotland, situated near the Campsie Fells and known for its scenic rural setting within the Stirling area.
-
D.
Highfield
Highfield is one of Harare’s oldest and most populous high-density suburbs, historically known as a center of political activism in Zimbabwe.
-
E.
Highfield
Highfield is a residential neighbourhood within the town of Bicester in Oxfordshire, 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_69e0b4c4cc648190b45fda6e2b20af56 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c1d6bdcc8190ba42c44159a2c0d5 |
completed | April 21, 2026, 12:16 a.m. |
Created at: April 16, 2026, 12:27 p.m.