Triple
T10569759
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Swale |
E249446
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Sittingbourne |
E48172
|
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: Sittingbourne | Statement: [The Swale, near, Sittingbourne]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sittingbourne Context triple: [The Swale, near, Sittingbourne]
-
A.
Sittingbourne
chosen
Sittingbourne is an industrial and commuter town in southeast England, located in the county of Kent.
-
B.
Sittingbourne and Sheppey
Sittingbourne and Sheppey is a UK parliamentary constituency in Kent that covers the town of Sittingbourne and the Isle of Sheppey.
-
C.
Swanscombe
Swanscombe is a town in Kent, England, known for its archaeological significance and proximity to major transport links including Ebbsfleet International railway station.
-
D.
Uckfield
Uckfield is a small market town in East Sussex, England, known for its historic high street and role as a local commercial and commuter hub.
-
E.
Henham
Henham is a small rural village located in the English county of Suffolk.
- 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_69d381c8bd708190acf3d275c908251e |
completed | April 6, 2026, 9:50 a.m. |
| NER | Named-entity recognition | batch_69d52730fd4481908b3f4eb80ca209f2 |
completed | April 7, 2026, 3:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e343cd76448190b0583cc15005ac9d |
completed | April 18, 2026, 8:41 a.m. |
Created at: April 6, 2026, 12:37 p.m.