Triple
T31943033
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sanjūsangen-dō |
E815576
|
entity |
| Predicate | hasCentralImage |
P1183
|
FINISHED |
| Object | seated Thousand-armed Kannon |
—
|
NE NERFINISHED |
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: seated Thousand-armed Kannon | Statement: [Sanjūsangen-dō, hasCentralImage, seated Thousand-armed Kannon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCentralImage Context triple: [Sanjūsangen-dō, hasCentralImage, seated Thousand-armed Kannon]
-
A.
hasCentralFigure
chosen
Indicates that something features a primary or most important figure at its core or focus.
-
B.
hasImageFeature
Indicates that an entity is associated with a specific visual characteristic or attribute extracted from an image.
-
C.
containsImage
Indicates that one entity includes or embeds an image as part of its content or structure.
-
D.
hasCentralSite
Indicates that an entity possesses or is associated with a primary or main site that serves as its central location or hub.
-
E.
hasCentralAct
Indicates that an entity includes or is characterized by a primary or most important action, event, or operation at its core.
- 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_69f348f42d188190a33fc8d20ec50517 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f7805ce6208190ac6dbd9c97989978 |
completed | May 3, 2026, 5:05 p.m. |
| PD | Predicate disambiguation | batch_69f77956ec648190ba4fb7e9d83fd107 |
completed | May 3, 2026, 4:35 p.m. |
Created at: May 1, 2026, 12:06 a.m.