Triple
T23346147
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | University of Occupational and Environmental Health, Japan |
E591870
|
entity |
| Predicate | hasFaculty |
P141
|
FINISHED |
| Object | School of Health Sciences |
—
|
NE NERFINISHED |
How this triple was built (3 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: School of Health Sciences | Statement: [University of Occupational and Environmental Health, Japan, hasFaculty, School of Health Sciences]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: School of Health Sciences Context triple: [University of Occupational and Environmental Health, Japan, hasFaculty, School of Health Sciences]
-
A.
School of Health Sciences
The School of Health Sciences is a college-level division of Seattle Pacific University that offers professional and academic programs in health-related fields such as nursing and allied health.
-
B.
School of Health Sciences
The School of Health Sciences is an academic division of the University of South Dakota that offers professional and graduate programs preparing students for careers in various health-related fields.
-
C.
School of Health Sciences
The School of Health Sciences is an academic division of Russell Sage College that offers professional and graduate programs preparing students for careers in healthcare and related fields.
-
D.
School of Health Sciences
The School of Health Sciences is an academic unit of Near East University that offers education and training in various health-related disciplines and professions.
-
E.
School of Health Sciences
The School of Health Sciences is a faculty of the University of Iceland that focuses on education and research in health-related disciplines such as medicine, nursing, and allied health professions.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: School of Health Sciences Target entity description: The School of Health Sciences is an academic division of the University of Occupational and Environmental Health, Japan, dedicated to education and research in health-related professions and disciplines.
-
A.
School of Health Sciences
The School of Health Sciences is a faculty of Showa University in Japan that specializes in education and research for allied health and medical professionals.
-
B.
School of Health Sciences
The School of Health Sciences is a faculty of Sapporo Medical University that focuses on education and research in allied health and clinical support professions.
-
C.
School of Health Sciences
The School of Health Sciences is a faculty of the University of Hyogo’s Port Island campus that specializes in education and research related to health and medical sciences.
-
D.
School of Health Sciences
The School of Health Sciences is an academic division of the University of Ioannina that focuses on education and research in medical and health-related disciplines.
-
E.
School of Health Sciences
The School of Health Sciences is an academic division of the University of Thessaly that offers education and research programs in health-related disciplines such as medicine, nursing, and allied health professions.
- F. None of above. chosen
Provenance (2 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_69e25d20e3d08190bcede87673cafb25 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f19837874481908f1a530261a34819 |
completed | April 29, 2026, 5:33 a.m. |
Created at: April 17, 2026, 5:19 p.m.