Triple
T11246073
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 法学研究科 |
E266207
|
entity |
| Predicate | キャンパス |
P269
|
FINISHED |
| Object |
東北大学川内キャンパス
東北大学川内キャンパスは、仙台市青葉区に位置し、人文社会系学部・研究科を中心とする東北大学の主要キャンパスの一つです。
|
E914082
|
NE FINISHED |
How this triple was built (4 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: 東北大学川内キャンパス | Statement: [法学研究科, キャンパス, 東北大学川内キャンパス]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 東北大学川内キャンパス Context triple: [法学研究科, キャンパス, 東北大学川内キャンパス]
-
A.
Sapporo Campus
Sapporo Campus is the main campus of Hokkaido University, known for its spacious, park-like grounds in central Sapporo and its mix of historic and modern academic facilities.
-
B.
Hakodate Campus
Hakodate Campus is a coastal branch of Hokkaido University known for its focus on marine science and fisheries-related research and education.
-
C.
Nagoya Institute of Technology
Nagoya Institute of Technology is a Japanese national university in Nagoya renowned for its engineering and technology education and research.
-
D.
Hodogaya Campus
Hodogaya Campus is the main campus of Yokohama National University, located in the Hodogaya ward of Yokohama, Japan.
-
E.
Shirokanedai Campus
Shirokanedai Campus is one of the University of Tokyo’s smaller specialized campuses, known for hosting advanced research institutes and graduate programs in a central Tokyo location.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: 東北大学川内キャンパス Triple: [法学研究科, キャンパス, 東北大学川内キャンパス]
Generated description
東北大学川内キャンパスは、仙台市青葉区に位置し、人文社会系学部・研究科を中心とする東北大学の主要キャンパスの一つです。
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: 東北大学川内キャンパス Target entity description: 東北大学川内キャンパスは、仙台市青葉区に位置し、人文社会系学部・研究科を中心とする東北大学の主要キャンパスの一つです。
-
A.
Sapporo Campus
Sapporo Campus is the main campus of Hokkaido University, known for its spacious, park-like grounds in central Sapporo and its mix of historic and modern academic facilities.
-
B.
Hakodate Campus
Hakodate Campus is a coastal branch of Hokkaido University known for its focus on marine science and fisheries-related research and education.
-
C.
Nagoya Institute of Technology
Nagoya Institute of Technology is a Japanese national university in Nagoya renowned for its engineering and technology education and research.
-
D.
Hodogaya Campus
Hodogaya Campus is the main campus of Yokohama National University, located in the Hodogaya ward of Yokohama, Japan.
-
E.
Shirokanedai Campus
Shirokanedai Campus is one of the University of Tokyo’s smaller specialized campuses, known for hosting advanced research institutes and graduate programs in a central Tokyo location.
- F. None of above. chosen
Provenance (5 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_69d6aac7953c8190b82caf9d7640fdf9 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e91c045c81908a9024a8aee32f4d |
completed | April 9, 2026, 5:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e4cc69402c8190be8785f892a41c7b |
completed | April 19, 2026, 12:36 p.m. |
| NEDg | Description generation | batch_69e4d9eb79608190b7ed108906f4e2bf |
completed | April 19, 2026, 1:34 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69e4df50eebc8190a4fe0aba7dc9fa62 |
completed | April 19, 2026, 1:57 p.m. |
Created at: April 8, 2026, 9:31 p.m.