Triple
T25647669
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 大日本帝国 |
E643007
|
entity |
| Predicate | 宗教政策 |
P7601
|
FINISHED |
| Object | 国家神道 |
—
|
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: 国家神道 | Statement: [大日本帝国, 宗教政策, 国家神道]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 宗教政策 Context triple: [大日本帝国, 宗教政策, 国家神道]
-
A.
religionPolicy
chosen
Indicates the stance, rules, or approach an entity adopts toward religious beliefs, practices, or institutions.
-
B.
相关政策
Indicates that there exists a relevant or associated policy that applies to, governs, or influences the specified entity or situation.
-
C.
dominantReligionPolicy
Indicates the policy or stance an authority adopts toward the religion that holds dominant or majority status within a given context.
-
D.
religiousPolicyOutcome
Indicates the consequences or effects that a particular religious policy has on individuals, groups, or society.
-
E.
recognizedReligionPolicy
Indicates that a governing authority has an official policy specifying which religions are formally recognized and how they are treated or regulated.
- 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_69e77e7ce28081908b08d65ee6e5c8be |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f5faa6399c8190b24bba1b8ccc7bdc |
completed | May 2, 2026, 1:22 p.m. |
| PD | Predicate disambiguation | batch_69f4807f8680819098a524158d049c63 |
completed | May 1, 2026, 10:29 a.m. |
Created at: April 21, 2026, 5:57 p.m.