Triple
T23840134
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Column of Marcus Aurelius spiral reliefs |
E590963
|
entity |
| Predicate | visualTechnique |
P14965
|
FINISHED |
| Object | low relief |
—
|
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: low relief | Statement: [Column of Marcus Aurelius spiral reliefs, visualTechnique, low relief]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: visualTechnique Context triple: [Column of Marcus Aurelius spiral reliefs, visualTechnique, low relief]
-
A.
artisticTechnique
chosen
Indicates the method, style, or process used to create or execute an artistic work.
-
B.
specialEffectsTechnique
Indicates a relationship where a particular special effects method or process is used to create or enhance visual or auditory effects in a production.
-
C.
filmingTechnique
Indicates the specific method or style used to capture visual content during the filming process.
-
D.
visualTechnology
Indicates a relationship where one entity is a technology used to capture, process, display, or otherwise handle visual information for another entity or context.
-
E.
featuresTechnique
Indicates that something incorporates or makes use of a particular technique as part of its content or execution.
- 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_69e25d1de32c8190a907afe9c3d6cd6d |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c886aab081909ad896abe383afb9 |
completed | April 29, 2026, 8:59 a.m. |
| PD | Predicate disambiguation | batch_69f156036ad48190bc2ffdaf39218bcb |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 8:08 p.m.