Triple
T2193618
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kyushu University Hospital |
E49919
|
entity |
| Predicate | teachesDiscipline |
P21344
|
FINISHED |
| Object | medicine |
—
|
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: medicine | Statement: [Kyushu University Hospital, teachesDiscipline, medicine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: teachesDiscipline Context triple: [Kyushu University Hospital, teachesDiscipline, medicine]
-
A.
offersDiscipline
Indicates that one entity provides or makes available a particular field of study, training, or area of specialization to another entity.
-
B.
supportsDiscipline
Indicates that one entity provides assistance, resources, or endorsement that helps sustain or advance a particular discipline.
-
C.
teachesAbout
chosen
Indicates that one entity provides instruction or information to another entity on a particular subject or topic.
-
D.
coreTeaching
Indicates that an entity serves as a primary or foundational teaching or instructional activity for another entity.
-
E.
featuredDiscipline
Indicates that one discipline is highlighted or given special prominence in relation to another entity or context.
- 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_69a88aaba3c48190b351cab9b26989ff |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abbf4a542881908aaaf4f0f85bc32c |
completed | March 7, 2026, 6:01 a.m. |
| PD | Predicate disambiguation | batch_69abbda52328819089c7ab111bebb0ca |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:46 p.m.