Triple

T13109787
Position Surface form Disambiguated ID Type / Status
Subject Birdo E310938 entity
Predicate voiceActorJapanese P99957 FINISHED
Object Akiko Koike
Akiko Koike is a Japanese voice actress known for providing the Japanese voice of the Nintendo character Birdo.
E1023031 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: Akiko Koike | Statement: [Birdo, voiceActorJapanese, Akiko Koike]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Akiko Koike
Context triple: [Birdo, voiceActorJapanese, Akiko Koike]
  • A. Yuriko Koike
    Yuriko Koike is a Japanese politician and former Tokyo governor known for her reformist agenda and for founding the national political party Party of Hope.
  • B. Erika Koike
    Erika Koike is a professional makeup artist best known for her brief, highly publicized marriage to actor Nicolas Cage.
  • C. Yuko Kishida
    Yuko Kishida is the wife of Japanese Prime Minister Fumio Kishida and serves as Japan’s First Lady, engaging in various diplomatic and public activities.
  • D. Haruka Satō
    Haruka Satō is a Japanese individual notable enough to be recognized as a bearer of the common surname Satō.
  • E. Miyuki Hatoyama
    Miyuki Hatoyama is a Japanese former actress and television personality known for her unconventional, spiritual views and high-profile role as the wife of former Prime Minister Yukio Hatoyama.
  • 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: Akiko Koike
Triple: [Birdo, voiceActorJapanese, Akiko Koike]
Generated description
Akiko Koike is a Japanese voice actress known for providing the Japanese voice of the Nintendo character Birdo.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Akiko Koike
Target entity description: Akiko Koike is a Japanese voice actress known for providing the Japanese voice of the Nintendo character Birdo.
  • A. Yuriko Koike
    Yuriko Koike is a Japanese politician and former Tokyo governor known for her reformist agenda and for founding the national political party Party of Hope.
  • B. Erika Koike
    Erika Koike is a professional makeup artist best known for her brief, highly publicized marriage to actor Nicolas Cage.
  • C. Yuko Kishida
    Yuko Kishida is the wife of Japanese Prime Minister Fumio Kishida and serves as Japan’s First Lady, engaging in various diplomatic and public activities.
  • D. Haruka Satō
    Haruka Satō is a Japanese individual notable enough to be recognized as a bearer of the common surname Satō.
  • E. Miyuki Hatoyama
    Miyuki Hatoyama is a Japanese former actress and television personality known for her unconventional, spiritual views and high-profile role as the wife of former Prime Minister Yukio Hatoyama.
  • 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_69d806a872d08190a329806f8ff30df4 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d9817e4f408190b77c198b4157d77a completed April 10, 2026, 11:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6e27d8110819087ade3537f867ae0 completed May 3, 2026, 5:51 a.m.
NEDg Description generation batch_69f6e4c5e2888190b0bfcdf2cc25ad5f completed May 3, 2026, 6:01 a.m.
NED2 Entity disambiguation (via description) batch_69f6e5979df881909db42a735b9b1064 completed May 3, 2026, 6:05 a.m.
Created at: April 9, 2026, 9:05 p.m.