Triple
T7228505
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Japanese constitutional law |
E154842
|
entity |
| Predicate | academicFieldStudiedAt |
P2582
|
FINISHED |
| Object | Japanese law faculties |
—
|
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: Japanese law faculties | Statement: [Japanese constitutional law, academicFieldStudiedAt, Japanese law faculties]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: academicFieldStudiedAt Context triple: [Japanese constitutional law, academicFieldStudiedAt, Japanese law faculties]
-
A.
academicFocus
Indicates the primary field of study, discipline, or subject area that an entity concentrates on academically.
-
B.
hasSubjectOfStudy
Indicates that an entity (such as a person or organization) focuses on, researches, or specializes in a particular field or topic of study.
-
C.
educationField
Indicates the academic or professional discipline in which an entity has been educated or trained.
-
D.
studiedUnder
Indicates that one entity received instruction, training, or mentorship from another, typically in an academic or apprenticeship context.
-
E.
offersFieldOfStudy
chosen
Indicates that an institution or program provides a particular field of study as an available area of academic focus.
- 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_69c68811dd1c8190ac460bb39e64e1f0 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6e9e0ba248190a57a3b4fa8b858c7 |
completed | March 27, 2026, 8:34 p.m. |
| PD | Predicate disambiguation | batch_69c6e761b7fc8190857794d78af1b468 |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 2:54 p.m.