Triple
T27932258
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cholmondeley Castle |
E708012
|
entity |
| Predicate | hasBuildingOnEstate |
P14728
|
FINISHED |
| Object | Cholmondeley Chapel |
—
|
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: Cholmondeley Chapel | Statement: [Cholmondeley Castle, hasBuildingOnEstate, Cholmondeley Chapel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBuildingOnEstate Context triple: [Cholmondeley Castle, hasBuildingOnEstate, Cholmondeley Chapel]
-
A.
hasBuildingOnIsland
Indicates that a particular building is located on or associated with a specific island.
-
B.
hasBuildingStatus
Indicates the current condition, classification, or operational state assigned to a building.
-
C.
hasBuildingFrom
Indicates a relationship where a location or site possesses or includes a building that originates from, or was constructed in, a specified time period, source, or context.
-
D.
buildingOwned
Indicates that one entity possesses legal ownership rights over a building associated with another entity.
-
E.
containsBuilding
chosen
Indicates that one location or area includes a building within its boundaries.
- 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_69ef96bbf2c48190a9d0e0291457aab6 |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69f68f670b608190a0b6ab60d722b4e0 |
completed | May 2, 2026, 11:57 p.m. |
| PD | Predicate disambiguation | batch_69f68b78f29481908cc8f390496dee97 |
completed | May 2, 2026, 11:40 p.m. |
Created at: April 27, 2026, 7:03 p.m.