Triple
T1338135
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gallery of Honour |
E28401
|
entity |
| Predicate | curatorialFocus |
P18101
|
FINISHED |
| Object | seventeenth-century Dutch 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: seventeenth-century Dutch painting | Statement: [Gallery of Honour, curatorialFocus, seventeenth-century Dutch painting]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: curatorialFocus Context triple: [Gallery of Honour, curatorialFocus, seventeenth-century Dutch painting]
-
A.
museumFocus
Indicates that a museum is primarily dedicated to or specializes in a particular subject, theme, or type of collection.
-
B.
hasExhibitionFocus
chosen
Indicates that an exhibition is primarily centered on, or thematically dedicated to, a particular subject, medium, or focus area.
-
C.
hasCuratorialDepartment
Indicates that an item or entity is associated with a specific curatorial department responsible for its care, management, or interpretation.
-
D.
curatedBy
Indicates that something has been selectively organized, managed, or assembled by a particular agent or entity.
-
E.
exhibitionType
Indicates the specific category or kind of exhibition associated with an entity (e.g., art show, trade fair, scientific exhibit).
- 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_69a49854eb3481908c7d56b2e449a290 |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c2115d388190b031ae2de1296f8a |
completed | March 1, 2026, 10:47 p.m. |
| PD | Predicate disambiguation | batch_69a4bef174708190a07bbc697fe19a2d |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:56 p.m.