Triple

T12859478
Position Surface form Disambiguated ID Type / Status
Subject The Last Samurai E307546 entity
Predicate castMember P1668 FINISHED
Object Koyuki
Koyuki is a Japanese actress and model best known internationally for her role opposite Tom Cruise in the film "The Last Samurai."
 E1022938 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: Koyuki | Statement: [The Last Samurai, castMember, Koyuki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Koyuki
Context triple: [The Last Samurai, castMember, Koyuki]
  • A. Tsutako
    Tsutako is a Japanese given name, most notably borne by Tsutako Nakasone.
  • B. Yuki
    The Yuki are a Native American people indigenous to what is now Northern California, traditionally living in the upper Eel River region with distinct languages and cultural practices.
  • C. Tsubami
    Tsubami is one of the official bird mascots of the Tokyo Yakult Swallows baseball team, known for her cute design and energetic support of the club.
  • D. Kodama Yūki
    Kodama Yūki is a Japanese individual notable for bearing the surname Kodama, though specific widely recognized biographical or professional details are not well documented in major public sources.
  • E. Mayu
    Mayu is a regional dialect of the Berta language, spoken by Berta communities in parts of northeastern Africa.
  • 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: Koyuki
Triple: [The Last Samurai, castMember, Koyuki]
Generated description
Koyuki is a Japanese actress and model best known internationally for her role opposite Tom Cruise in the film "The Last Samurai."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Koyuki
Target entity description: Koyuki is a Japanese actress and model best known internationally for her role opposite Tom Cruise in the film "The Last Samurai."
  • A. Tsutako
    Tsutako is a Japanese given name, most notably borne by Tsutako Nakasone.
  • B. Yuki
    The Yuki are a Native American people indigenous to what is now Northern California, traditionally living in the upper Eel River region with distinct languages and cultural practices.
  • C. Tsubami
    Tsubami is one of the official bird mascots of the Tokyo Yakult Swallows baseball team, known for her cute design and energetic support of the club.
  • D. Kodama Yūki
    Kodama Yūki is a Japanese individual notable for bearing the surname Kodama, though specific widely recognized biographical or professional details are not well documented in major public sources.
  • E. Mayu
    Mayu is a regional dialect of the Berta language, spoken by Berta communities in parts of northeastern Africa.
  • 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_69d7bdf5e7cc8190be357278bc5ba3bb completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d970242bd48190941cbae0315ebc3d completed April 10, 2026, 9:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6e260b824819083e90333827d0833 completed May 3, 2026, 5:51 a.m.
NEDg Description generation batch_69f6e49f9b2c8190adc17603ac326b94 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, 5:37 p.m.