Triple

T12650944
Position Surface form Disambiguated ID Type / Status
Subject 韓国統監 E302155 entity
Predicate 初代 P106004 FINISHED
Object 伊藤博文
伊藤博文は、明治維新を主導し日本の近代国家体制を築いた中心的政治家であり、初代内閣総理大臣としても知られる人物である。
E994520 NE FINISHED

How this triple was built (5 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: 伊藤博文 | Statement: [韓国統監, 初代, 伊藤博文]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 伊藤博文
Context triple: [韓国統監, 初代, 伊藤博文]
  • A. 原敬
    原敬は、大正時代に日本初の本格的な政党内閣を率いた立憲政友会の政治家であり、第19代内閣総理大臣を務めた人物である。
  • B. 吉田 茂
    吉田 茂は、戦後日本の復興と独立回復を主導し、サンフランシスコ講和条約の締結などで知られる日本の政治家・第45・48–51代内閣総理大臣です。
  • C. 犬養毅
    犬養毅は、昭和初期に政党政治を主導しながら五・一五事件で暗殺された日本の内閣総理大臣である。
  • D. 樺山資紀
    樺山資紀 was a Meiji-era Japanese naval officer and statesman who served as the first Governor-General of Taiwan and later as Minister of the Navy.
  • E. 岸信介
    岸信介は、戦後日本の保守政治を主導し日米安全保障条約改定を推進したことで知られる第56・57代内閣総理大臣である。
  • 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: 伊藤博文
Triple: [韓国統監, 初代, 伊藤博文]
Generated description
伊藤博文は、明治維新を主導し日本の近代国家体制を築いた中心的政治家であり、初代内閣総理大臣としても知られる人物である。
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: 伊藤博文
Target entity description: 伊藤博文は、明治維新を主導し日本の近代国家体制を築いた中心的政治家であり、初代内閣総理大臣としても知られる人物である。
  • A. 原敬
    原敬は、大正時代に日本初の本格的な政党内閣を率いた立憲政友会の政治家であり、第19代内閣総理大臣を務めた人物である。
  • B. 吉田 茂
    吉田 茂は、戦後日本の復興と独立回復を主導し、サンフランシスコ講和条約の締結などで知られる日本の政治家・第45・48–51代内閣総理大臣です。
  • C. 犬養毅
    犬養毅は、昭和初期に政党政治を主導しながら五・一五事件で暗殺された日本の内閣総理大臣である。
  • D. 樺山資紀
    樺山資紀 was a Meiji-era Japanese naval officer and statesman who served as the first Governor-General of Taiwan and later as Minister of the Navy.
  • E. 岸信介
    岸信介は、戦後日本の保守政治を主導し日米安全保障条約改定を推進したことで知られる第56・57代内閣総理大臣である。
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: 初代
Context triple: [韓国統監, 初代, 伊藤博文]
  • A. codenameOfFirstGeneration
    Indicates that one entity is the codename assigned to the first generation of another entity.
  • B. firstGenerationReleaseDate
    Indicates the calendar date on which the first generation or initial version of something was officially released.
  • C. firstGenerationStart
    Indicates the point in time or event at which the first generation in a sequence, lineage, or series begins.
  • D. firstAVA
    Indicates that the subject is the first entity (e.g., version, appearance, or instance) in a sequence associated with the object.
  • E. firstGenerationEngine
    Indicates that the engine belongs to the first generation in a series of engine designs or development iterations.
  • 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_69d7bded71a88190bb76e2413af9ea66 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d9617b07ec8190b714f04ae6654060 completed April 10, 2026, 8:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6687dad6c8190bb72bfebf6636a37 completed May 2, 2026, 9:11 p.m.
NEDg Description generation batch_69f6697d8ac88190b4ead9ce47f3a705 completed May 2, 2026, 9:15 p.m.
NED2 Entity disambiguation (via description) batch_69f66a2fa350819091f12e16d59c2278 completed May 2, 2026, 9:18 p.m.
PD Predicate disambiguation batch_69d960b78ce8819091f15dd5013e6da5 completed April 10, 2026, 8:42 p.m.
PDg Predicate description generation batch_69d96179c7648190a05a13991d62bebb completed April 10, 2026, 8:45 p.m.
Created at: April 9, 2026, 5:18 p.m.