Triple
T35389898
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St Mary the Virgin Church, East Bergholt |
E1022900
|
entity |
| Predicate | hasBellTowerType |
P48866
|
FINISHED |
| Object | detached wooden bell cage |
—
|
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: detached wooden bell cage | Statement: [St Mary the Virgin Church, East Bergholt, hasBellTowerType, detached wooden bell cage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBellTowerType Context triple: [St Mary the Virgin Church, East Bergholt, hasBellTowerType, detached wooden bell cage]
-
A.
hasBellTower
Indicates that one entity (typically a building or structure) possesses or includes a bell tower as part of it.
-
B.
hasBellTowerCount
Indicates the number of bell towers that an entity possesses or is associated with.
-
C.
hasBellTowerLocation
Indicates the specific location where a bell tower is situated or attached relative to another structure or place.
-
D.
hasBellTowerUse
Indicates that an entity is used as, or functions in the capacity of, a bell tower.
-
E.
bellTowerStyle
chosen
Indicates the architectural style or design type of a bell tower in relation to a building or structure.
- 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_69f76df34ba48190bd80f0814cdcd540 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fcab6e888881908ca9e18660928a40 |
completed | May 7, 2026, 3:10 p.m. |
| PD | Predicate disambiguation | batch_69fc4562a5b88190bad48f083a6dcdfa |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 3, 2026, 4:03 p.m.