Triple
T18010488
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Port of Garston |
E430864
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Garston |
—
|
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: Garston | Statement: [Port of Garston, locatedIn, Garston]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Garston Context triple: [Port of Garston, locatedIn, Garston]
-
A.
Garston
Garston is a suburban area and residential locality within the county of Hertfordshire in England.
-
B.
Hamstead
Hamstead is a suburban residential area in the West Midlands, England, situated between Birmingham and Sandwell.
-
C.
Garston and Halewood
chosen
Garston and Halewood is a UK parliamentary constituency in Merseyside that includes parts of south Liverpool and surrounding areas.
-
D.
Ashtead
Ashtead is a large suburban village in Surrey, England, known for its residential character, local amenities, and proximity to the town of Leatherhead.
-
E.
Marston Green
Marston Green is a suburban village in the Metropolitan Borough of Solihull in the West Midlands, England, known for its residential character and proximity to Birmingham and the NEC.
- 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_69d8b904530081908bf341d842464856 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4b51f0a488190bd34e1f9039f4dc9 |
completed | April 19, 2026, 10:57 a.m. |
Created at: April 10, 2026, 10:24 a.m.