Triple
T790236
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southend Airport |
E16896
|
entity |
| Predicate | serves |
P98
|
FINISHED |
| Object | Southend-on-Sea |
E53391
|
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: Southend-on-Sea | Statement: [Southend Airport, serves, Southend-on-Sea]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Southend-on-Sea Context triple: [Southend Airport, serves, Southend-on-Sea]
-
A.
Southend-on-Sea
chosen
Southend-on-Sea is a coastal resort city in Essex, England, known for its seaside tourism and the world’s longest pleasure pier.
-
B.
Basildon
Basildon is a large town in Essex, England, known as a post-war new town and a major commercial and residential centre within the East of England.
-
C.
Clacton-on-Sea
Clacton-on-Sea is a seaside resort town on the Essex coast of England, known for its sandy beaches, pier, and traditional British holiday attractions.
-
D.
Margate
Margate is a historic seaside resort town on the north coast of Kent in southeast England, known for its sandy beaches, amusement attractions, and vibrant arts scene.
-
E.
Ramsgate
Ramsgate is a seaside town and port on the Isle of Thanet in Kent, England, known historically as a popular resort and maritime hub.
- 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_69a4936cb7448190914f5fe4b8d81607 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a7841b0c8190859ecd247e32c6ec |
completed | March 1, 2026, 8:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac118d9b408190b1dd9540386406f2 |
completed | March 7, 2026, 11:52 a.m. |
Created at: March 1, 2026, 7:38 p.m.