Triple

T2427844
Position Surface form Disambiguated ID Type / Status
Subject 東北大学 E53572 entity
Predicate キャンパス P269 FINISHED
Object 青葉山キャンパス
青葉山キャンパスは、自然豊かな丘陵地に広がる東北大学の主要キャンパスで、理系学部や研究施設が集積する拠点となっている。
E266206 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: 青葉山キャンパス | Statement: [東北大学, キャンパス, 青葉山キャンパス]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 青葉山キャンパス
Context triple: [東北大学, キャンパス, 青葉山キャンパス]
  • A. Senriyama Campus
    Senriyama Campus is the main campus of Kansai University in Osaka, Japan, housing its central academic, administrative, and student facilities.
  • B. Tsurumai Campus
    Tsurumai Campus is one of Nagoya University's main campuses, known especially for its medical and health-related faculties and facilities in Nagoya, Japan.
  • C. Seiryo Campus
    Seiryo Campus is one of Tohoku University's main campuses, known for housing its medical and health sciences faculties and related research facilities in Sendai, Japan.
  • D. Yoshida Campus
    Yoshida Campus is the main and historic campus of Kyoto University, located in Kyoto, Japan, and home to many of its core faculties and research facilities.
  • E. Kashiwa Campus
    Kashiwa Campus is a major research and education campus of the University of Tokyo located in Kashiwa, Chiba Prefecture, known for its advanced science and technology institutes.
  • 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: 青葉山キャンパス
Triple: [東北大学, キャンパス, 青葉山キャンパス]
Generated description
青葉山キャンパスは、自然豊かな丘陵地に広がる東北大学の主要キャンパスで、理系学部や研究施設が集積する拠点となっている。
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: 青葉山キャンパス
Target entity description: 青葉山キャンパスは、自然豊かな丘陵地に広がる東北大学の主要キャンパスで、理系学部や研究施設が集積する拠点となっている。
  • A. Senriyama Campus
    Senriyama Campus is the main campus of Kansai University in Osaka, Japan, housing its central academic, administrative, and student facilities.
  • B. Tsurumai Campus
    Tsurumai Campus is one of Nagoya University's main campuses, known especially for its medical and health-related faculties and facilities in Nagoya, Japan.
  • C. Seiryo Campus
    Seiryo Campus is one of Tohoku University's main campuses, known for housing its medical and health sciences faculties and related research facilities in Sendai, Japan.
  • D. Yoshida Campus
    Yoshida Campus is the main and historic campus of Kyoto University, located in Kyoto, Japan, and home to many of its core faculties and research facilities.
  • E. Kashiwa Campus
    Kashiwa Campus is a major research and education campus of the University of Tokyo located in Kashiwa, Chiba Prefecture, known for its advanced science and technology institutes.
  • 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_69ab495c44d48190b7235b23719bc3f6 completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abd0d942048190bc5c715faa850632 completed March 7, 2026, 7:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69aebf637be4819096874a24e87f84ab completed March 9, 2026, 12:38 p.m.
NEDg Description generation batch_69aec7698e9881909c75137cb5cf2a0c completed March 9, 2026, 1:13 p.m.
NED2 Entity disambiguation (via description) batch_69aec87df0648190b8099b4eaa3d9b22 completed March 9, 2026, 1:17 p.m.
Created at: March 6, 2026, 9:42 p.m.