Triple
T25952821
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brackish-Pond, Devonshire Parish, Bermuda |
E654008
|
entity |
| Predicate | relativeLocationWithinParish |
P178071
|
FINISHED |
| Object | central Devonshire Parish |
—
|
LITERAL FINISHED |
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: central Devonshire Parish | Statement: [Brackish-Pond, Devonshire Parish, Bermuda, relativeLocationWithinParish, central Devonshire Parish]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relativeLocationWithinParish Context triple: [Brackish-Pond, Devonshire Parish, Bermuda, relativeLocationWithinParish, central Devonshire Parish]
-
A.
nearParish
Indicates that one entity is geographically close to or in the vicinity of a specified parish.
-
B.
mainParishOf
chosen
Indicates that one parish serves as the primary or central parish associated with a given entity or area.
-
C.
hasNeighbouringParish
Indicates that one parish is directly adjacent to or borders another parish geographically.
-
D.
parishChurchLocation
Indicates the specific place where a parish church is situated or located.
-
E.
positionRelativeToTown
Indicates the spatial position or orientation of one place or object in relation to a specified town.
- 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_69e7ab40ac788190a771bc499eb1ae5f |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69fd884cb2b48190b6acd473430d9e19 |
completed | May 8, 2026, 6:53 a.m. |
| PD | Predicate disambiguation | batch_69fd8709ca208190a8bab836f0156af5 |
completed | May 8, 2026, 6:47 a.m. |
Created at: April 22, 2026, 8:44 a.m.