Triple
T8174826
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 小柴昌俊 |
E190914
|
entity |
| Predicate | 研究テーマ |
P24329
|
FINISHED |
| Object | ニュートリノの検出 |
—
|
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: ニュートリノの検出 | Statement: [小柴昌俊, 研究テーマ, ニュートリノの検出]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 研究テーマ Context triple: [小柴昌俊, 研究テーマ, ニュートリノの検出]
-
A.
researchTopic
chosen
Indicates that a subject conducts or focuses research on a particular topic or area of study.
-
B.
isSubjectOfStudy
Indicates that an entity is the focus or topic being examined, researched, or analyzed in a study or investigation.
-
C.
subjectOfWork
Indicates that one entity is the main topic, focus, or theme that a particular work (such as a book, article, or artwork) is about.
-
D.
usesResearchSubject
Indicates that one entity employs or utilizes another entity as a research subject in a study or investigation.
-
E.
coreThesis
Indicates that something expresses, embodies, or constitutes the central argument or main claim within a larger work, discussion, or theory.
- 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_69ca82c1c0a08190bf8692b4d91a03ca |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb480a7ac4819088fabd5bec6ba2e5 |
completed | March 31, 2026, 4:05 a.m. |
| PD | Predicate disambiguation | batch_69cb36a4c40c81909f60aef0e1624c13 |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:40 p.m.