Triple
T5013105
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eynsham |
E112672
|
entity |
| Predicate | hasNearbyVillage |
P4647
|
FINISHED |
| Object | Cassington |
E100776
|
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: Cassington | Statement: [Eynsham, hasNearbyVillage, Cassington]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cassington Context triple: [Eynsham, hasNearbyVillage, Cassington]
-
A.
Cassington
chosen
Cassington is a small rural village in Oxfordshire, England, known for its historic church and traditional English countryside setting.
-
B.
Coryton
Coryton is a suburban area and railway terminus in Cardiff, Wales, served by local commuter trains.
-
C.
Bolsover
Bolsover is a historic market town in England best known for its hilltop Bolsover Castle and its location within the county of Derbyshire.
-
D.
Knighton
Knighton is a small market town on the English–Welsh border, known for its position on Offa’s Dyke and its surrounding rural landscapes.
-
E.
Cowlinge
Cowlinge is a small rural village and civil parish located in the county of Suffolk in eastern England.
- 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_69bd4434acb8819086679dbeccc2fe54 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd730f12a481908a27c15dc73987c6 |
completed | March 20, 2026, 4:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be9271eccc8190bbe9bdb876b41cb8 |
completed | March 21, 2026, 12:43 p.m. |
Created at: March 20, 2026, 1:35 p.m.