Triple
T20120109
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bamberg Cathedral |
E490581
|
entity |
| Predicate | artStyleOfInterior |
P5509
|
FINISHED |
| Object | Romanesque sculpture |
—
|
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: Romanesque sculpture | Statement: [Bamberg Cathedral, artStyleOfInterior, Romanesque sculpture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: artStyleOfInterior Context triple: [Bamberg Cathedral, artStyleOfInterior, Romanesque sculpture]
-
A.
interiorStyle
chosen
Indicates that one entity has a particular interior design style or aesthetic characterized by the other entity.
-
B.
partOfInteriorDesign
Indicates that one entity is a component or element within the interior design scheme of another entity.
-
C.
interiorDecoratedBy
Indicates that the interior of a space or structure has been designed or decorated by a specific agent or entity.
-
D.
typicalInterior
Indicates that one entity is the usual or characteristic interior of another entity.
-
E.
interiorOrganization
Indicates how the internal parts or elements of something are arranged, structured, or organized in relation to one another.
- 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_69da62636cc08190982cc71733a17b8d |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e6673cfaac81909d6216f3e37c2439 |
completed | April 20, 2026, 5:49 p.m. |
| PD | Predicate disambiguation | batch_69e54cf788188190a46cc49c9ce7617f |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 11:30 p.m.