Triple

T6267140
Position Surface form Disambiguated ID Type / Status
Subject Henry Miller E140440 entity
Predicate spouse P13 FINISHED
Object Hoki Tokuda
Hoki Tokuda was a Japanese-born jazz singer and artist best known as the much younger third wife of American writer Henry Miller.
E581188 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: Hoki Tokuda | Statement: [Henry Miller, spouse, Hoki Tokuda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hoki Tokuda
Context triple: [Henry Miller, spouse, Hoki Tokuda]
  • A. Wakatoshi
    Wakatoshi is a fictional volleyball player from the manga and anime series "Haikyuu!!", known as the powerful ace and captain of Shiratorizawa Academy.
  • B. Takahito
    Takahito, better known by his title Prince Mikasa, was a member of the Japanese imperial family and the youngest son of Emperor Taishō.
  • C. Munetaka
    Munetaka is a Japanese professional baseball slugger best known for his record-setting home run power in Nippon Professional Baseball.
  • D. Hisashi
    Hisashi is a Japanese masculine given name borne by various notable individuals in fields such as law, politics, sports, and the arts.
  • E. Taro Kono
    Taro Kono is a prominent Japanese politician and Liberal Democratic Party member known for serving in key cabinet posts such as foreign minister and defense minister and for his reformist, media-savvy profile.
  • 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: Hoki Tokuda
Triple: [Henry Miller, spouse, Hoki Tokuda]
Generated description
Hoki Tokuda was a Japanese-born jazz singer and artist best known as the much younger third wife of American writer Henry Miller.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hoki Tokuda
Target entity description: Hoki Tokuda was a Japanese-born jazz singer and artist best known as the much younger third wife of American writer Henry Miller.
  • A. Wakatoshi
    Wakatoshi is a fictional volleyball player from the manga and anime series "Haikyuu!!", known as the powerful ace and captain of Shiratorizawa Academy.
  • B. Takahito
    Takahito, better known by his title Prince Mikasa, was a member of the Japanese imperial family and the youngest son of Emperor Taishō.
  • C. Munetaka
    Munetaka is a Japanese professional baseball slugger best known for his record-setting home run power in Nippon Professional Baseball.
  • D. Hisashi
    Hisashi is a Japanese masculine given name borne by various notable individuals in fields such as law, politics, sports, and the arts.
  • E. Taro Kono
    Taro Kono is a prominent Japanese politician and Liberal Democratic Party member known for serving in key cabinet posts such as foreign minister and defense minister and for his reformist, media-savvy profile.
  • 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_69c008cabc4081909723e2547c9d6cc0 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c063a0f2548190a2f5c307bc5a67cf completed March 22, 2026, 9:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69c51939cc6081909e491bd16fab595b completed March 26, 2026, 11:32 a.m.
NEDg Description generation batch_69c51c246b9c8190b22bc1afedd1956c completed March 26, 2026, 11:44 a.m.
NED2 Entity disambiguation (via description) batch_69c51c9cc3488190abc90abe9ae2050b completed March 26, 2026, 11:46 a.m.
Created at: March 22, 2026, 4:25 p.m.