Triple
T30785834
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 広島市現代美術館 |
E783951
|
entity |
| Predicate | 企画展 |
P8907
|
FINISHED |
| Object | 国内外の現代美術展覧会 |
—
|
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: 国内外の現代美術展覧会 | Statement: [広島市現代美術館, 企画展, 国内外の現代美術展覧会]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 企画展 Context triple: [広島市現代美術館, 企画展, 国内外の現代美術展覧会]
-
A.
organizedExhibitionsIn
Indicates that an entity arranged, coordinated, or managed exhibitions that took place in a specified location or venue.
-
B.
exhibitionConcept
Indicates that one entity serves as the conceptual theme, idea, or curatorial framework underlying an exhibition associated with another entity.
-
C.
exhibitionFunction
Indicates that one entity serves as the function, role, or purpose of an exhibition associated with another entity.
-
D.
exhibition
chosen
Indicates that an entity is organizing, hosting, or serving as a public display or presentation of another entity (such as artworks, objects, or information).
-
E.
exhibitionSeries
Indicates that multiple exhibitions are related and organized as parts of the same overarching series or program.
- 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_69f224b213c8819083886073f90b647e |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f68fe8168c8190b083be0e33988b9c |
completed | May 2, 2026, 11:59 p.m. |
| PD | Predicate disambiguation | batch_69f686140aa08190a35f62572b2db9b6 |
completed | May 2, 2026, 11:17 p.m. |
Created at: April 29, 2026, 8:41 p.m.