Triple
T24551640
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karowei Dorgu |
E607385
|
entity |
| Predicate | servedInParish |
P136612
|
FINISHED |
| Object | St Mark’s Church, Tollington Park |
—
|
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: St Mark’s Church, Tollington Park | Statement: [Karowei Dorgu, servedInParish, St Mark’s Church, Tollington Park]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servedInParish Context triple: [Karowei Dorgu, servedInParish, St Mark’s Church, Tollington Park]
-
A.
servedInDiocese
Indicates that one entity held a role or performed official duties within the jurisdiction of a particular diocese.
-
B.
churchServed
chosen
Indicates that one entity has provided religious service, ministry, or leadership within the other entity’s church or congregation.
-
C.
parishIncludes
Indicates that a parish geographically or administratively contains or encompasses another entity or area.
-
D.
hasParishFunction
Indicates that an entity performs, fulfills, or is assigned a specific functional role within a parish.
-
E.
parish
Indicates that an entity is administratively or ecclesiastically associated with a particular parish.
- 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_69e2c4cae1b88190825e88d5ce8aa61e |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2a8cdb6b88190ad17a9b3ba607fb3 |
completed | April 30, 2026, 12:56 a.m. |
| PD | Predicate disambiguation | batch_69f2a6b99e7c8190ba7e2dc8729a314a |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:27 a.m.