Triple
T30785835
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 広島市現代美術館 |
E783951
|
entity |
| Predicate | ワークショップ |
P56397
|
FINISHED |
| Object | 市民向け教育普及プログラム |
—
|
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: 市民向け教育普及プログラム | Statement: [広島市現代美術館, ワークショップ, 市民向け教育普及プログラム]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ワークショップ Context triple: [広島市現代美術館, ワークショップ, 市民向け教育普及プログラム]
-
A.
workshopInTitleIndicates
Indicates that the presence of the word "workshop" in a title signifies that the associated event, session, or item is a workshop.
-
B.
notableWorkshop
Indicates that an entity is a workshop distinguished by particular significance, prominence, or recognition (e.g., in impact, reputation, or importance).
-
C.
workshopMark
Indicates that an entity has been designated, labeled, or flagged in the context of a workshop-related process or activity.
-
D.
hasWorkshopsAt
chosen
Indicates that an entity conducts, hosts, or offers workshops at a specified location or venue.
-
E.
workshopOrStudio
Indicates that one entity functions as a workshop or studio associated with, used by, or belonging to 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_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.