Triple

T36803954
Position Surface form Disambiguated ID Type / Status
Subject 大隅良典 E909393 entity
Predicate 師事先 P186315 FINISHED
Object 小谷正雄研究室（東京大学）
小谷正雄研究室（東京大学）は、ノーベル賞受賞者・大隅良典らを輩出した、東京大学における生物学・生命科学分野の先駆的研究室である。
 E2199167 NE FINISHED

How this triple was built (3 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: 小谷正雄研究室（東京大学） | Statement: [大隅良典, 師事先, 小谷正雄研究室（東京大学）]
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: 小谷正雄研究室（東京大学）
Triple: [大隅良典, 師事先, 小谷正雄研究室（東京大学）]
Generated description
小谷正雄研究室（東京大学）は、ノーベル賞受賞者・大隅良典らを輩出した、東京大学における生物学・生命科学分野の先駆的研究室である。
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: 師事先
Context triple: [大隅良典, 師事先, 小谷正雄研究室（東京大学）]
  • A. 開山
    Indicates initiating or founding a new temple, monastery, or religious site, often as its first head or spiritual leader.
  • B. 開基
    Indicates the act of founding or establishing something for the first time, such as initiating a lineage, enterprise, or domain.
  • C. 先祖職務
    Indicates that an ancestor of the person held or performed a particular office, role, or duty.
  • D. 築城者
    Indicates the agent or person responsible for constructing or building a castle or fortress.
  • E. 最終階級
    Indicates the final or highest rank/grade an entity ultimately attains in a hierarchical system.
  • F. None of above. chosen

Provenance (7 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_69f76e7b98888190899b6478a82ad6ae completed May 3, 2026, 3:49 p.m.
NER Named-entity recognition batch_69f7cabdd2d88190be1c8de7e499cb83 completed May 3, 2026, 10:22 p.m.
NED1 Entity disambiguation (via context triple) batch_6a3d17b20bac8190bb73387ece847ddd completed June 25, 2026, 11:57 a.m.
NEDg Description generation batch_6a3d18e02fdc8190bded018c870e7e53 completed June 25, 2026, 12:02 p.m.
NED2 Entity disambiguation (via description) batch_6a3d647697248190a8d3561f8986f0ff completed June 25, 2026, 5:25 p.m.
PD Predicate disambiguation batch_69f7c89b528c8190bf80b230fc7c7108 completed May 3, 2026, 10:13 p.m.
PDg Predicate description generation batch_69f7ca91f1808190b2a05c4b691da0bb completed May 3, 2026, 10:22 p.m.
Created at: May 3, 2026, 4:12 p.m.