Triple
T7766068
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Norwich Cathedral |
E176147
|
entity |
| Predicate | hasCloisterWalks |
P17704
|
FINISHED |
| Object | four cloister walks |
—
|
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: four cloister walks | Statement: [Norwich Cathedral, hasCloisterWalks, four cloister walks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCloisterWalks Context triple: [Norwich Cathedral, hasCloisterWalks, four cloister walks]
-
A.
hasCloister
chosen
Indicates that one entity possesses or includes a cloister as part of its structure or layout.
-
B.
hasCloisterFromCentury
Indicates that an entity possesses a cloister that dates from, or was constructed in, a specified century.
-
C.
hasPromenade
Indicates that one entity features or includes a promenade, typically as a designated walkway or leisure area associated with it.
-
D.
hasCorridor
Indicates that one entity includes, is connected by, or provides access through a corridor to another entity.
-
E.
hasPavilion
Indicates that one entity possesses, includes, or is associated with a pavilion as part of its structure, property, or facilities.
- 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_69c69962923c8190ac74d28b4f9fe0a0 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c7043279748190b30882e9cc6cca54 |
completed | March 27, 2026, 10:26 p.m. |
| PD | Predicate disambiguation | batch_69c7016f4ce881909c2e9f610255187b |
completed | March 27, 2026, 10:15 p.m. |
Created at: March 27, 2026, 4:09 p.m.