Triple
T3298017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Temple of Peace |
E69262
|
entity |
| Predicate | builtInStyle |
P13268
|
FINISHED |
| Object | Imperial Roman architecture |
—
|
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: Imperial Roman architecture | Statement: [Temple of Peace, builtInStyle, Imperial Roman architecture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: builtInStyle Context triple: [Temple of Peace, builtInStyle, Imperial Roman architecture]
-
A.
builtIn
Indicates that one entity is inherently included as a standard, pre-existing component or feature of another entity, rather than being added or installed separately.
-
B.
structuralStyle
Indicates the architectural or design style that characterizes the structure or form of an entity.
-
C.
structureStyle
chosen
Indicates the architectural or design style characterizing how a structure is built or formed.
-
D.
usesAsStyleOf
Indicates that one entity adopts or applies another entity as a stylistic model, method, or manner of expression.
-
E.
styledAs
Indicates that one entity is presented, formatted, or designed in the manner, appearance, or aesthetic of another entity.
- 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_69ad859e529c8190a404273f53cb487d |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb0a2f4708190821edb9700f62d2f |
completed | March 8, 2026, 5:23 p.m. |
| PD | Predicate disambiguation | batch_69ada42407dc81909f60d7a14e1b7934 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:10 p.m.