Triple
T12059108
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karamon gate |
E287118
|
entity |
| Predicate | ornamentationTechnique |
P14965
|
FINISHED |
| Object | relief carving |
—
|
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: relief carving | Statement: [Karamon gate, ornamentationTechnique, relief carving]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ornamentationTechnique Context triple: [Karamon gate, ornamentationTechnique, relief carving]
-
A.
ornamentationStyle
Indicates the decorative design or stylistic approach applied as ornamentation to an entity.
-
B.
hasOrnamentation
Indicates that an entity possesses decorative features or embellishments applied to its surface or structure.
-
C.
notableOrnamental
Indicates that something is recognized as a particularly significant or distinguished example of ornamental decoration or design.
-
D.
artisticTechnique
chosen
Indicates the method, style, or process used to create or execute an artistic work.
-
E.
decorativeComplexity
Indicates the degree or richness of ornamental detail or embellishment present in something.
- 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_69d6ab4780948190bdb9f7620c2ac27e |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9100b4ca8819084845ca4c13e34ce |
completed | April 10, 2026, 2:58 p.m. |
| PD | Predicate disambiguation | batch_69d902bda47c8190b94860b31df4a98c |
completed | April 10, 2026, 2:01 p.m. |
Created at: April 8, 2026, 9:47 p.m.