Triple
T8657663
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Osaka Tenmangū |
E205460
|
entity |
| Predicate | hasGuardianRole |
P52530
|
FINISHED |
| Object | protector of scholars |
—
|
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: protector of scholars | Statement: [Osaka Tenmangū, hasGuardianRole, protector of scholars]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGuardianRole Context triple: [Osaka Tenmangū, hasGuardianRole, protector of scholars]
-
A.
hasGuardianCommunity
Indicates that an entity is under the protection, oversight, or care of a specific guardian community.
-
B.
hasGuardianFigureType
chosen
Indicates the type or role of a guardian figure associated with an entity.
-
C.
hasCustodyRole
Indicates that one entity holds a specific custodial responsibility or role in relation to another entity.
-
D.
hasLegalRole
Indicates that an entity holds a specific legal capacity, status, or function in relation to another entity or context.
-
E.
hasSafetyRole
Indicates that an entity holds a responsibility or function related to safety within a given context or system.
- 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_69ca8350897c819086cde7596fbe5fe7 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc486d576081908ad28749c7971432 |
completed | March 31, 2026, 10:19 p.m. |
| PD | Predicate disambiguation | batch_69cc45619460819091e83ffdec99c865 |
completed | March 31, 2026, 10:06 p.m. |
Created at: March 30, 2026, 6:30 p.m.