Triple

T15620287
Position Surface form Disambiguated ID Type / Status
Subject Shohei E375532 entity
Predicate possibleKanjiSpelling P17917 FINISHED
Object 昇平
昇平 is a Japanese given name typically read as "Shohei," often carrying connotations of rising prosperity or peaceful advancement depending on the chosen kanji.
E1168675 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: 昇平 | Statement: [Shohei, possibleKanjiSpelling, 昇平]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 昇平
Context triple: [Shohei, possibleKanjiSpelling, 昇平]
  • A. 勝也
    勝也 is a masculine Japanese given name typically written with kanji conveying meanings related to "victory" or "winning."
  • B. 成城
    成城 is an upscale residential neighborhood in Tokyo known for its quiet streets, affluent homes, and proximity to Seijo Gakuen educational institutions.
  • C.
    晉 is the Chinese name of the ancient State of Jin, a major feudal power during the Spring and Autumn period of Chinese history.
  • D. 上皇
    上皇は日本において天皇が退位した後に名乗る称号で、現役の天皇とは区別される前天皇の身分を指す。
  • E. 尚書
    尚書 is one of the Five Classics of ancient Chinese literature, consisting of a collection of historical documents and speeches attributed to early Chinese rulers and officials.
  • 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: 昇平
Triple: [Shohei, possibleKanjiSpelling, 昇平]
Generated description
昇平 is a Japanese given name typically read as "Shohei," often carrying connotations of rising prosperity or peaceful advancement depending on the chosen kanji.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: 昇平
Target entity description: 昇平 is a Japanese given name typically read as "Shohei," often carrying connotations of rising prosperity or peaceful advancement depending on the chosen kanji.
  • A. 勝也
    勝也 is a masculine Japanese given name typically written with kanji conveying meanings related to "victory" or "winning."
  • B. 成城
    成城 is an upscale residential neighborhood in Tokyo known for its quiet streets, affluent homes, and proximity to Seijo Gakuen educational institutions.
  • C.
    晉 is the Chinese name of the ancient State of Jin, a major feudal power during the Spring and Autumn period of Chinese history.
  • D. 上皇
    上皇は日本において天皇が退位した後に名乗る称号で、現役の天皇とは区別される前天皇の身分を指す。
  • E. 尚書
    尚書 is one of the Five Classics of ancient Chinese literature, consisting of a collection of historical documents and speeches attributed to early Chinese rulers and officials.
  • 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_69d85ccf2794819096cda4cbcb02d478 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e997ce481909b2f10d25705fbc6 completed April 16, 2026, 2:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff5f3b643c819093230df6cfe440b9 completed May 9, 2026, 4:22 p.m.
NEDg Description generation batch_69ff5fea7cb48190a1acb9201a12fa32 completed May 9, 2026, 4:25 p.m.
NED2 Entity disambiguation (via description) batch_69ff62e84bec81908a4885bf7f8f3749 completed May 9, 2026, 4:38 p.m.
Created at: April 10, 2026, 4:13 a.m.