Triple

T13810419
Position Surface form Disambiguated ID Type / Status
Subject Kiyonori Kikutake E331873 entity
Predicate nativeName P15 FINISHED
Object 菊竹清訓
菊竹清訓 was a pioneering Japanese architect and leading figure of the Metabolist movement, known for visionary, modular designs that explored flexible and expandable urban structures.
E1062142 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: 菊竹清訓 | Statement: [Kiyonori Kikutake, nativeName, 菊竹清訓]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 菊竹清訓
Context triple: [Kiyonori Kikutake, nativeName, 菊竹清訓]
  • A. 竹下 登
    竹下 登 was a Japanese politician who served as Prime Minister of Japan from 1987 to 1989 and was a key figure in the Liberal Democratic Party.
  • B. 栗林貞子
    栗林貞子は、第二次世界大戦中の硫黄島守備隊司令官として知られる日本陸軍大将・栗林忠道の家族の一員である女性である。
  • C. 斎藤秀雄
    斎藤秀雄 was a prominent Japanese cellist and conductor, best known as a co-founder and influential teacher at the Toho Gakuen School of Music.
  • D. 成澤廣修
    成澤廣修は、日本の政治家で、東京都文京区の区政を長年担ってきた区長として知られている人物である。
  • E. 吉田遠志
    吉田遠志 was a prominent 20th-century Japanese woodblock print artist known for his landscape and animal prints that blended traditional ukiyo-e techniques with modern sensibilities.
  • 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: 菊竹清訓
Triple: [Kiyonori Kikutake, nativeName, 菊竹清訓]
Generated description
菊竹清訓 was a pioneering Japanese architect and leading figure of the Metabolist movement, known for visionary, modular designs that explored flexible and expandable urban structures.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: 菊竹清訓
Target entity description: 菊竹清訓 was a pioneering Japanese architect and leading figure of the Metabolist movement, known for visionary, modular designs that explored flexible and expandable urban structures.
  • A. 竹下 登
    竹下 登 was a Japanese politician who served as Prime Minister of Japan from 1987 to 1989 and was a key figure in the Liberal Democratic Party.
  • B. 栗林貞子
    栗林貞子は、第二次世界大戦中の硫黄島守備隊司令官として知られる日本陸軍大将・栗林忠道の家族の一員である女性である。
  • C. 斎藤秀雄
    斎藤秀雄 was a prominent Japanese cellist and conductor, best known as a co-founder and influential teacher at the Toho Gakuen School of Music.
  • D. 成澤廣修
    成澤廣修は、日本の政治家で、東京都文京区の区政を長年担ってきた区長として知られている人物である。
  • E. 吉田遠志
    吉田遠志 was a prominent 20th-century Japanese woodblock print artist known for his landscape and animal prints that blended traditional ukiyo-e techniques with modern sensibilities.
  • 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_69d81c59f8808190a851bc56afdc55e9 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de026ff6b481908066d6bf27064417 completed April 14, 2026, 9:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7b09161108190abbd97a30af9ab49 completed May 3, 2026, 8:31 p.m.
NEDg Description generation batch_69f7b138fda88190b2b7ffb51ce02a40 completed May 3, 2026, 8:34 p.m.
NED2 Entity disambiguation (via description) batch_69f7b28ca218819097fc35042d3b278a completed May 3, 2026, 8:39 p.m.
Created at: April 9, 2026, 10:12 p.m.