Triple
T21439585
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 農学部 |
E528902
|
entity |
| Predicate | 典型的な学科 |
P11940
|
FINISHED |
| Object | 農学科 |
—
|
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: 農学科 | Statement: [農学部, 典型的な学科, 農学科]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 典型的な学科 Context triple: [農学部, 典型的な学科, 農学科]
-
A.
studiedByDiscipline
Indicates that a subject (such as a phenomenon, object, or concept) is examined, analyzed, or researched within a particular academic or professional discipline.
-
B.
subDisciplineOf
Indicates that one discipline is a more specialized or narrower field within another, broader discipline.
-
C.
typicalCourse
chosen
Indicates that one entity is a standard or commonly taken course associated with another entity, such as a program, curriculum, or field of study.
-
D.
widelyStudiedIn
Indicates that something has been extensively researched, analyzed, or examined within a particular field, domain, or context.
-
E.
governingDiscipline
Indicates that one discipline or field provides the primary rules, principles, or framework that regulate or guide another activity, domain, or practice.
- 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_69e0c4569fa081908101baa24f8745db |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e8b6feb2e48190ba5649f16a8bbbda |
completed | April 22, 2026, 11:54 a.m. |
| PD | Predicate disambiguation | batch_69e61639ee288190889ffd500d1260f6 |
completed | April 20, 2026, 12:04 p.m. |
Created at: April 16, 2026, 6:05 p.m.