Triple
T20086004
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bernheim-Jeune family |
E496129
|
entity |
| Predicate | gallerySpecialization |
P91702
|
FINISHED |
| Object | modern 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: modern painting | Statement: [Bernheim-Jeune family, gallerySpecialization, modern painting]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: gallerySpecialization Context triple: [Bernheim-Jeune family, gallerySpecialization, modern painting]
-
A.
gallerySpace
Indicates that one entity serves as a gallery or exhibition space for displaying the other entity.
-
B.
portraitSpecialization
Indicates that one entity specializes in creating or working with portraits, distinguishing a focused area of expertise within a broader artistic or professional domain.
-
C.
exhibitionFeature
Indicates that an exhibition includes or highlights a particular item, work, or element as one of its featured components.
-
D.
artSpecialty
chosen
Indicates that an entity’s primary focus, expertise, or specialization is in a particular art form or artistic domain.
-
E.
exhibitionDiscipline
Indicates the academic or artistic field that characterizes or organizes an exhibition.
- 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_69da626eee3881909f3454986d4a6511 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6655ae9ec8190bde2f17452639de8 |
completed | April 20, 2026, 5:41 p.m. |
| PD | Predicate disambiguation | batch_69e54cf369b88190931532420517dac7 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 10:58 p.m.