Triple
T19995739
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 早稲田大学大学院法学研究科 |
E494187
|
entity |
| Predicate | parentOrganization |
P254
|
FINISHED |
| Object | 早稲田大学法学部 |
—
|
NE NERFINISHED |
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: 早稲田大学法学部 | Statement: [早稲田大学大学院法学研究科, parentOrganization, 早稲田大学法学部]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 早稲田大学法学部 Context triple: [早稲田大学大学院法学研究科, parentOrganization, 早稲田大学法学部]
-
A.
早稲田大学大学院法学研究科
早稲田大学大学院法学研究科 is the graduate-level law school of Waseda University in Japan, offering advanced legal education and research programs.
-
B.
早稲田大学第二文学部
早稲田大学第二文学部は、東京都新宿区に所在する早稲田大学にかつて設置されていた夜間主コース中心の人文・社会系学部で、多くの政治家や文化人を輩出したことで知られる学部である。
-
C.
早稲田大学理工学部
早稲田大学理工学部は、東京都に位置する早稲田大学の理工系学部で、工学・基礎科学・先端技術分野の教育と研究で知られる学部です。
-
D.
Faculty of Law, Waseda University
chosen
The Faculty of Law at Waseda University is a leading Japanese law school known for its comprehensive legal education, influential scholarship, and strong contributions to the country’s legal and political spheres.
-
E.
Keio University Faculty of Law
Keio University Faculty of Law is a leading Japanese law school within Keio University, renowned for its rigorous legal education and influential role in training lawyers, policymakers, and scholars.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69da626b2d748190886981ea90c8b2ea |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e65fe3fb288190a935c334e8a5d54e |
completed | April 20, 2026, 5:18 p.m. |
Created at: April 11, 2026, 3:32 p.m.