Triple
T4885364
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blue and Green Music |
E109425
|
entity |
| Predicate | hasExhibitionContext |
P53388
|
FINISHED |
| Object | exhibited in major O’Keeffe retrospectives |
—
|
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: exhibited in major O’Keeffe retrospectives | Statement: [Blue and Green Music, hasExhibitionContext, exhibited in major O’Keeffe retrospectives]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasExhibitionContext Context triple: [Blue and Green Music, hasExhibitionContext, exhibited in major O’Keeffe retrospectives]
-
A.
hasExhibition
Indicates that an entity organizes, hosts, or presents a particular exhibition.
-
B.
hasExhibitionScope
chosen
Indicates the thematic, geographic, temporal, or conceptual range and boundaries that define what an exhibition covers.
-
C.
hasExhibitionFocus
Indicates that an exhibition is primarily centered on, or thematically dedicated to, a particular subject, medium, or focus area.
-
D.
hasExhibitionModel
Indicates that one entity serves as the exhibition or display model associated with another entity.
-
E.
hasExhibitionsAbout
Indicates that one entity organizes or presents exhibitions whose subject matter concerns another entity.
- 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_69bd440f71348190b99938e59fb7f9a1 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6de3718881908521968fa6e6b444 |
completed | March 20, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69bd6c2be5e881909f6ec9c3bcde49f3 |
completed | March 20, 2026, 3:47 p.m. |
Created at: March 20, 2026, 1:27 p.m.