Triple
T33952531
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Doncaster Mansion House |
E870476
|
entity |
| Predicate | locationOnStreet |
—
|
GENERATED |
| Object | High Street, Doncaster |
—
|
UNRECOGNIZED GENERATED |
How this triple was built (1 step)
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.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationOnStreet Context triple: [Doncaster Mansion House, locationOnStreet, High Street, Doncaster]
-
A.
streetLocation
chosen
Indicates that one entity is located on, along, or at a specific street associated with the other entity.
-
B.
streetOrArea
Indicates that one entity is a street or area associated with, located at, or relevant to the other entity.
-
C.
locatedBetweenStreets
Indicates that something is situated between two specified streets, with its position bounded or defined by those streets.
-
D.
locationOnSquare
Indicates that one entity is positioned on a specific square region or cell within a larger spatial grid or board.
-
E.
locationAddressed
Indicates that a communication, message, or action is specifically directed to or intended for a particular location or address.
- F. None of above.
Provenance (1 batch)
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_69f3499c2d7481909c953a5010227725 |
completed | April 30, 2026, 12:22 p.m. |
Created at: May 1, 2026, 1:49 a.m.