Triple
T670107
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Byzantine architecture |
E12950
|
entity |
| Predicate | structuralInnovation |
P1484
|
FINISHED |
| Object | use of pendentives to support domes |
—
|
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: use of pendentives to support domes | Statement: [Byzantine architecture, structuralInnovation, use of pendentives to support domes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: structuralInnovation Context triple: [Byzantine architecture, structuralInnovation, use of pendentives to support domes]
-
A.
innovation
chosen
Indicates the introduction or development of something new or significantly improved compared to existing methods, products, or ideas.
-
B.
architecturalConcept
Indicates that one entity represents or embodies an architectural concept in relation to another entity.
-
C.
innovationArea
Indicates the thematic or domain-specific field in which an innovation is focused or applied.
-
D.
architecturalWork
Indicates that one entity is an architectural creation (such as a building or structure) designed or realized by another entity.
-
E.
designEvolution
Indicates how the design of an entity changes, develops, or is refined over time or across versions.
- 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_69a493355dec819098d4244b2fa34885 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4a1b3682c8190a9b9a454480c3446 |
completed | March 1, 2026, 8:29 p.m. |
| PD | Predicate disambiguation | batch_69a49d1a16c48190af89e3b078a4957e |
completed | March 1, 2026, 8:10 p.m. |
Created at: March 1, 2026, 7:36 p.m.