Triple
T30131140
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Swindon Rural District |
E765848
|
entity |
| Predicate | hadBoundaryRelationWith |
P117759
|
FINISHED |
| Object | borough of Swindon |
—
|
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: borough of Swindon | Statement: [Swindon Rural District, hadBoundaryRelationWith, borough of Swindon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadBoundaryRelationWith Context triple: [Swindon Rural District, hadBoundaryRelationWith, borough of Swindon]
-
A.
hasBorderRelation
Indicates that one entity shares a boundary or border with another entity.
-
B.
previouslyPartOfBoundaryBetween
Indicates that something once formed part of the dividing line or border between two areas or entities, but no longer does so.
-
C.
hasBoundaryInfluenceFrom
Indicates that the boundary or limits of one entity are affected, shaped, or determined by another entity.
-
D.
hasConceptualBoundary
Indicates that one entity defines, marks, or establishes the abstract limit or scope of another entity’s meaning, applicability, or conceptual extent.
-
E.
adminBoundaryRelation
chosen
Indicates a relationship where one entity defines, delimits, or is associated with the administrative boundary of another 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_69f22477d1a081908df2b7e6ed16859d |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67e48471c8190b3b488c00f5d0b37 |
completed | May 2, 2026, 10:44 p.m. |
| PD | Predicate disambiguation | batch_69f673c664f08190b4d66cdc305e10db |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 7:15 p.m.