Triple
T37734266
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bodai Daruma |
E940236
|
entity |
| Predicate | inJapaneseArt |
P188984
|
FINISHED |
| Object | frequently portrayed in ink paintings |
—
|
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: frequently portrayed in ink paintings | Statement: [Bodai Daruma, inJapaneseArt, frequently portrayed in ink paintings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inJapaneseArt Context triple: [Bodai Daruma, inJapaneseArt, frequently portrayed in ink paintings]
-
A.
inJapaneseCulture
chosen
Indicates that something holds, appears, or is understood specifically within the context of Japanese culture.
-
B.
mainJapaneseGateway
Indicates that one entity serves as the primary Japanese access point or entry gateway for another entity.
-
C.
inJapaneseHistory
Indicates that something occurs within, belongs to, or is specifically situated in the context of Japanese history.
-
D.
publicArt
Indicates that something is an artwork installed or displayed in a publicly accessible space.
-
E.
inArtSince
Indicates that an entity has been involved or active in the field of art starting from a specified time.
- 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_69f76edefd048190a32212c5c3919531 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbb9e8108c8190ae1c7940b1677e95 |
completed | May 6, 2026, 10 p.m. |
| PD | Predicate disambiguation | batch_69fbb141605c8190b9c27d70352522db |
completed | May 6, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:18 p.m.