Triple
T36031271
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Elizabeth West |
E1042264
|
entity |
| Predicate | formerNameOfAreaNowIn |
P43887
|
FINISHED |
| Object | Edinburgh North |
—
|
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: Edinburgh North | Statement: [Elizabeth West, formerNameOfAreaNowIn, Edinburgh North]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerNameOfAreaNowIn Context triple: [Elizabeth West, formerNameOfAreaNowIn, Edinburgh North]
-
A.
formerNameOfAreaWithin
Indicates that one area previously had a different name while remaining within the same larger encompassing area.
-
B.
formerNameOfRegion
Indicates that one name was previously used for a region that is now known by a different name.
-
C.
formerNameOfDistrict
chosen
Indicates that one district previously had a different official name, which is the value linked by this predicate.
-
D.
formerNameOfProvince
Indicates that one name was previously used as the official name of a province before being replaced by another name.
-
E.
formerNameOfJurisdiction
Indicates that one jurisdiction previously had a different official name, which is given by the related entity.
- F. None of above.
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_69f76e2c568881909e1e21f85252b0f0 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a0082989e6c819099fea0e706332e37 |
completed | May 10, 2026, 1:05 p.m. |
| PD | Predicate disambiguation | batch_6a0081ed6a1481908baf472876e28db9 |
completed | May 10, 2026, 1:02 p.m. |
Created at: May 3, 2026, 4:07 p.m.