Triple
T3070383
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cinque Ports |
E64004
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Bexhill |
E141152
|
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: Bexhill | Statement: [Cinque Ports, hasPart, Bexhill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bexhill Context triple: [Cinque Ports, hasPart, Bexhill]
-
A.
Bexhill-on-Sea
chosen
Bexhill-on-Sea is a seaside town in East Sussex, England, known for its Victorian and Edwardian architecture and the modernist De La Warr Pavilion on the south coast.
-
B.
Eastbourne
Eastbourne is a seaside town and popular coastal resort on England’s south coast, known for its Victorian architecture, long promenade, and proximity to the chalk cliffs of Beachy Head.
-
C.
Worthing
Worthing is a large seaside town and resort on the south coast of England in West Sussex.
-
D.
Bognor Regis
Bognor Regis is a seaside town and popular holiday resort on the south coast of England, known for its beaches and traditional British coastal attractions.
-
E.
Hove
Hove is a coastal town in East Sussex, England, forming part of the city of Brighton and Hove on the south coast.
- 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_69ad857a8aec8190bfdfd9c14554ac5a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada100f0b8819095da366fdc6803a8 |
completed | March 8, 2026, 4:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b20354031c819081a0852fe7e181ab |
completed | March 12, 2026, 12:05 a.m. |
Created at: March 8, 2026, 3:02 p.m.