Triple
T33773137
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cave of Swimmers |
E865438
|
entity |
| Predicate | hasFigureStyle |
P69931
|
FINISHED |
| Object | schematic human figures |
—
|
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: schematic human figures | Statement: [Cave of Swimmers, hasFigureStyle, schematic human figures]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFigureStyle Context triple: [Cave of Swimmers, hasFigureStyle, schematic human figures]
-
A.
hasStyle
Indicates that an entity possesses, exhibits, or is characterized by a particular style or manner.
-
B.
hasKeyFigure
Indicates that an entity includes, involves, or is characterized by an important or central person relevant to it.
-
C.
hasStructuralStyle
Indicates that one entity possesses, exhibits, or is characterized by a particular architectural or structural design style.
-
D.
hasPowerStyle
Indicates that one entity possesses or exhibits a particular style or manner of using power in relation to another entity or context.
-
E.
includesFigureType
chosen
Indicates that one entity contains or encompasses a specific type or category of figure within it.
- 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_69f3498df6f88190bf9647ea4e4a956e |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ff49f888348190b9c55afa73b99e6a |
completed | May 9, 2026, 2:51 p.m. |
| PD | Predicate disambiguation | batch_69ff49614ef88190ac70b034c55ad738 |
completed | May 9, 2026, 2:49 p.m. |
Created at: May 1, 2026, 1:45 a.m.