Triple
T30270756
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fréjus Cathedral |
E769786
|
entity |
| Predicate | cloisterFeature |
P128144
|
FINISHED |
| Object | painted wooden ceiling |
—
|
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: painted wooden ceiling | Statement: [Fréjus Cathedral, cloisterFeature, painted wooden ceiling]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cloisterFeature Context triple: [Fréjus Cathedral, cloisterFeature, painted wooden ceiling]
-
A.
cloisterConstruction
Indicates the construction or building activity specifically related to a cloister or cloistered architectural space.
-
B.
cloisterStyle
Indicates the architectural style or design characteristics of a cloister in relation to a building or site.
-
C.
cloisterDate
Indicates the date on which an entity was cloistered, enclosed, or formally withdrawn from public life.
-
D.
cloisterDesigner
Indicates a relationship where a designer is responsible for planning, creating, or shaping a cloister or cloister-like architectural space.
-
E.
cloisterDecoration
chosen
Indicates that one entity serves as a decorative element or motif specifically associated with a cloister or cloistered architectural space.
- 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_69f224856d9881908c7f0dd64f059672 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f680d43c708190a28635b6f09d3895 |
completed | May 2, 2026, 10:55 p.m. |
| PD | Predicate disambiguation | batch_69f678ce54b081908c26edfd49e39c60 |
completed | May 2, 2026, 10:21 p.m. |
Created at: April 29, 2026, 7:43 p.m.