Triple
T28790795
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 賴清德 |
E726945
|
entity |
| Predicate | 醫師專科 |
P466
|
FINISHED |
| Object | 復健科 |
—
|
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: 復健科 | Statement: [賴清德, 醫師專科, 復健科]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 醫師專科 Context triple: [賴清德, 醫師專科, 復健科]
-
A.
doctor
Indicates that one entity serves as a medical professional providing diagnosis, treatment, or healthcare services to another entity.
-
B.
medicalDegree
Indicates that an individual has obtained a formal medical qualification or degree from an accredited institution.
-
C.
medicalPractice
Indicates a relationship where an entity engages in or carries out the professional provision of medical care or services.
-
D.
supportsMedicalSpecialty
Indicates that one entity provides resources, infrastructure, or services that enable or facilitate the practice or development of a particular medical specialty.
-
E.
hasSpecialty
chosen
Indicates that an entity possesses a particular area of expertise, focus, or professional specialization.
- 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_69f0319aabec81908368720196f69a35 |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f658ee40088190b71e1219407690d0 |
completed | May 2, 2026, 8:05 p.m. |
| PD | Predicate disambiguation | batch_69f65760fd3081908ffe014a5e2bf069 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 28, 2026, 6:23 a.m.