Triple
T7551575
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 天神 |
E178545
|
entity |
| Predicate | 関連する分野 |
P6979
|
FINISHED |
| Object | 教育 |
—
|
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: 教育 | Statement: [天神, 関連する分野, 教育]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 関連する分野 Context triple: [天神, 関連する分野, 教育]
-
A.
relatedWorkField
Indicates that one work is associated with or pertains to the same or a relevant field, discipline, or area of activity as another work.
-
B.
relatedField
chosen
Indicates that one field, topic, or area of study is connected or relevant to another in subject matter or application.
-
C.
関連主題
Indicates that there exists a thematically or contextually related subject connected to the given entity.
-
D.
relatedStudy
Indicates that one study is connected or relevant to another study, typically through shared topics, methods, or findings.
-
E.
relatedRFC
Indicates that one resource or specification is connected or associated with another through a shared or relevant RFC (Request for Comments) document.
- 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_69c69f2cbe08819088f9eb0c03ef529b |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f8b6c6488190b8fd94aca6ea8486 |
completed | March 27, 2026, 9:37 p.m. |
| PD | Predicate disambiguation | batch_69c6f4daad6c8190af2b8ae88d2c8cb7 |
completed | March 27, 2026, 9:21 p.m. |
Created at: March 27, 2026, 3:49 p.m.