Triple
T22966398
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cattedrale di Santa Maria Assunta |
E571057
|
entity |
| Predicate | hasPortalSculpture |
P88225
|
FINISHED |
| Object | Romanesque reliefs |
—
|
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 reliefs | Statement: [Cattedrale di Santa Maria Assunta, hasPortalSculpture, Romanesque reliefs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPortalSculpture Context triple: [Cattedrale di Santa Maria Assunta, hasPortalSculpture, Romanesque reliefs]
-
A.
hasSculptureSubject
Indicates that a sculpture depicts, represents, or is thematically focused on a particular subject.
-
B.
hasSculptureType
Indicates that an entity is associated with a sculpture and specifies the type or category of that sculpture.
-
C.
hasSculptureStyle
Indicates that a sculpture is created in, or associated with, a particular artistic style or sculptural tradition.
-
D.
hasSculpturalFigures
chosen
Indicates that something includes or features three-dimensional sculpted figures as part of its form or decoration.
-
E.
hasSculptureMaterial
Indicates that a sculpture is made from, or incorporates, a specified material.
- 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_69e245b2c6548190a0e4c7f2f7df2d48 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1822e542c8190a865f18e64fc0768 |
completed | April 29, 2026, 3:59 a.m. |
| PD | Predicate disambiguation | batch_69ef3b9101f48190a06c69dff26c6441 |
completed | April 27, 2026, 10:33 a.m. |
Created at: April 17, 2026, 3:47 p.m.