Triple
T33463272
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Churches Conservation Trust |
E856978
|
entity |
| Predicate | typeOfBuildingCaredFor |
P156542
|
FINISHED |
| Object | Anglican churches |
—
|
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: Anglican churches | Statement: [The Churches Conservation Trust, typeOfBuildingCaredFor, Anglican churches]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfBuildingCaredFor Context triple: [The Churches Conservation Trust, typeOfBuildingCaredFor, Anglican churches]
-
A.
buildingTypeServed
chosen
Indicates the type of building that is served, supported, or catered to by a given entity or system.
-
B.
buildingType
Indicates the specific category or function that characterizes what kind of building something is.
-
C.
hasBuildingUnderCare
Indicates that an entity is responsible for the maintenance, management, or oversight of a particular building.
-
D.
intendedBuildingType
Indicates the type of building that something is planned or designed to be.
-
E.
typeOfBuildingOccupied
Indicates the specific kind or category of building that an entity occupies or uses.
- 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_69f34973461481909c701c98ebd75623 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a00b3d2e0c88190a8bf49576e654f64 |
completed | May 10, 2026, 4:35 p.m. |
| PD | Predicate disambiguation | batch_6a00b376f4e48190a6676779fe02ea9f |
completed | May 10, 2026, 4:33 p.m. |
Created at: May 1, 2026, 1:37 a.m.