Triple
T24552354
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Awaji Ningyō Jōruri puppet theater |
E607406
|
entity |
| Predicate | hasPuppetOperatorRole |
P52946
|
FINISHED |
| Object | omozukai |
—
|
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: omozukai | Statement: [Awaji Ningyō Jōruri puppet theater, hasPuppetOperatorRole, omozukai]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPuppetOperatorRole Context triple: [Awaji Ningyō Jōruri puppet theater, hasPuppetOperatorRole, omozukai]
-
A.
hasOwnerOperator
Indicates that an entity is owned and operated by a specified party, combining both ownership and operational responsibility in a single relationship.
-
B.
isPuppetLeader
Indicates that one entity serves as a leader who is controlled or heavily influenced by another, rather than acting independently.
-
C.
mayBeOperatedBy
chosen
Indicates that an entity has the potential or permission to be operated, controlled, or run by another entity.
-
D.
hasLegalRole
Indicates that an entity holds a specific legal capacity, status, or function in relation to another entity or context.
-
E.
hasPrimaryAccessRole
Indicates that an entity is assigned the main or most authoritative access role governing its permissions or privileges.
- 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_69e2c4cae1b88190825e88d5ce8aa61e |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2a8cdb6b88190ad17a9b3ba607fb3 |
completed | April 30, 2026, 12:56 a.m. |
| PD | Predicate disambiguation | batch_69f2a6b99e7c8190ba7e2dc8729a314a |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:27 a.m.