Triple

T11246052
Position Surface form Disambiguated ID Type / Status
Subject 青葉山キャンパス E266206 entity
Predicate 関連組織 P629 FINISHED
Object 東北大学金属材料研究所 E53584 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: 東北大学金属材料研究所 | Statement: [青葉山キャンパス, 関連組織, 東北大学金属材料研究所]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: 東北大学金属材料研究所
Context triple: [青葉山キャンパス, 関連組織, 東北大学金属材料研究所]
  • A. 東北大学
    東北大学は、日本の宮城県仙台市に本部を置く、研究力と工学・理学分野で特に高い評価を受ける国立総合大学です。
  • B. Department of Materials Engineering, The University of Tokyo
    The Department of Materials Engineering at the University of Tokyo is a leading academic department focused on the science, engineering, and innovation of advanced materials for technology and industry.
  • C. Kyushu University Institute for Materials Chemistry and Engineering
    Kyushu University Institute for Materials Chemistry and Engineering is a research institute specializing in advanced materials science and chemical engineering within Kyushu University.
  • D. Institute for Materials Research chosen
    The Institute for Materials Research is a leading Japanese research center at Tohoku University specializing in advanced materials science and engineering.
  • E. National Institute for Materials Science
    The National Institute for Materials Science is a leading Japanese research organization dedicated to advanced materials science and technology development.
  • 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_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_69e4ad8c3bec8190987451ab73e79011 completed April 19, 2026, 10:25 a.m.
Created at: April 8, 2026, 9:31 p.m.