Triple
T5201638
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leo Castelli Gallery |
E117405
|
entity |
| Predicate | exhibitedWorkType |
P3050
|
FINISHED |
| Object | painting |
—
|
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: painting | Statement: [Leo Castelli Gallery, exhibitedWorkType, painting]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: exhibitedWorkType Context triple: [Leo Castelli Gallery, exhibitedWorkType, painting]
-
A.
exhibitsWorkOf
Indicates that one entity displays or presents the creative works produced by another entity.
-
B.
exhibitionType
Indicates the specific category or kind of exhibition associated with an entity (e.g., art show, trade fair, scientific exhibit).
-
C.
exhibitedAs
Indicates that something is presented or displayed in a particular context, such as in a show, gallery, or exhibition.
-
D.
exhibitionMedium
Indicates the material or format through which something is exhibited or displayed.
-
E.
artworkType
chosen
Indicates the specific category or kind of artwork that characterizes the relationship between the subject and the artwork.
- 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_69bd4463dd3c81909966123f20b79d57 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7adb034c819086bf8a85fbf158f4 |
completed | March 20, 2026, 4:50 p.m. |
| PD | Predicate disambiguation | batch_69bd77b9a67c8190819612257ea746b4 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:47 p.m.