Triple
T7825736
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Department of Materials Engineering, University of Tokyo |
E181239
|
entity |
| Predicate | affiliation |
P10
|
FINISHED |
| Object | School of Engineering, University of Tokyo |
E708132
|
NE 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: School of Engineering, University of Tokyo | Statement: [Department of Materials Engineering, University of Tokyo, affiliation, School of Engineering, University of Tokyo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: School of Engineering, University of Tokyo Context triple: [Department of Materials Engineering, University of Tokyo, affiliation, School of Engineering, University of Tokyo]
-
A.
Faculty of Engineering, The University of Tokyo
The Faculty of Engineering at the University of Tokyo is a leading Japanese engineering faculty renowned for its cutting-edge research and education across a wide range of engineering disciplines.
-
B.
Graduate School of Engineering, The University of Tokyo
chosen
The Graduate School of Engineering at the University of Tokyo is a leading Japanese engineering institution renowned for its advanced research and education across a wide range of engineering and technology disciplines.
-
C.
Institute of Industrial Science, University of Tokyo
The Institute of Industrial Science at the University of Tokyo is a leading Japanese research institute dedicated to advanced science and engineering, spanning fields from information technology and robotics to materials and environmental studies.
-
D.
Research Center for Advanced Science and Technology, University of Tokyo
The Research Center for Advanced Science and Technology at the University of Tokyo is a leading interdisciplinary institute focused on pioneering research and innovation across cutting-edge fields in science and technology.
-
E.
Tokyo Institute of Technology
Tokyo Institute of Technology is a leading Japanese national research university renowned for its strengths in science, engineering, and technology.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca8282ccec819083c48efb72d21cf9 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb04a6185481908462079bd2827642 |
completed | March 30, 2026, 11:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce4d3697848190be759069962a8f00 |
completed | April 2, 2026, 11:04 a.m. |
Created at: March 30, 2026, 4:43 p.m.