Triple
T23323308
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harwich Navyard Wharf |
E591216
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | Harwich town centre |
—
|
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: Harwich town centre | Statement: [Harwich Navyard Wharf, adjacentTo, Harwich town centre]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harwich town centre Context triple: [Harwich Navyard Wharf, adjacentTo, Harwich town centre]
-
A.
Harwich
Harwich is a coastal town on southeastern Cape Cod in Massachusetts known for its beaches, harbors, and summer tourism.
-
B.
Harwich
chosen
Harwich is a historic port town in Essex, England, which once served as a parliamentary borough represented in the British House of Commons.
-
C.
Walmington-on-Sea
Walmington-on-Sea is a fictional English seaside town best known as the home of the bumbling Home Guard platoon in the Dad’s Army franchise.
-
D.
Harleston
Harleston is a village and civil parish located in the county of Suffolk in eastern England.
-
E.
Harleston
Harleston is a small market town in Norfolk, England, known for its historic architecture and rural surroundings.
- 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_69e25d1effe4819096907f95f610dbff |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1978731b0819090f92ef768f2a749 |
completed | April 29, 2026, 5:30 a.m. |
Created at: April 17, 2026, 5:07 p.m.