Triple

T20595973
Position Surface form Disambiguated ID Type / Status
Subject Princess Ayako of Takamado E506049 entity
Predicate spouse P13 FINISHED
Object Kei Moriya
Kei Moriya is a Japanese commoner and businessman best known for marrying Princess Ayako of Takamado, a member of Japan’s imperial family.
E1567537 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: Kei Moriya | Statement: [Princess Ayako of Takamado, spouse, Kei Moriya]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kei Moriya
Context triple: [Princess Ayako of Takamado, spouse, Kei Moriya]
  • A. Mirai Yamamoto
    Mirai Yamamoto is a Japanese actress known for her roles in film and television since the late 1990s.
  • B. Yuto Nakamura
    Yuto Nakamura is a Japanese given name bearer, likely known as a public figure such as an athlete, entertainer, or professional in Japan.
  • C. Tatsuya Mihashi
    Tatsuya Mihashi was a Japanese film and television actor known for his roles in postwar Japanese cinema and appearances in international productions.
  • D. Yusuke Nakamura
    Yusuke Nakamura is a Japanese illustrator and graphic designer renowned for his distinctive, colorful artwork used in album covers, book jackets, and anime-related projects.
  • E. Shota Saito
    Shota Saito is an actor best known for his role in the cult-favorite action-comedy film "Scott Pilgrim vs. the World."
  • 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: Kei Moriya
Triple: [Princess Ayako of Takamado, spouse, Kei Moriya]
Generated description
Kei Moriya is a Japanese commoner and businessman best known for marrying Princess Ayako of Takamado, a member of Japan’s imperial family.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kei Moriya
Target entity description: Kei Moriya is a Japanese commoner and businessman best known for marrying Princess Ayako of Takamado, a member of Japan’s imperial family.
  • A. Mirai Yamamoto
    Mirai Yamamoto is a Japanese actress known for her roles in film and television since the late 1990s.
  • B. Yuto Nakamura
    Yuto Nakamura is a Japanese given name bearer, likely known as a public figure such as an athlete, entertainer, or professional in Japan.
  • C. Tatsuya Mihashi
    Tatsuya Mihashi was a Japanese film and television actor known for his roles in postwar Japanese cinema and appearances in international productions.
  • D. Yusuke Nakamura
    Yusuke Nakamura is a Japanese illustrator and graphic designer renowned for his distinctive, colorful artwork used in album covers, book jackets, and anime-related projects.
  • E. Shota Saito
    Shota Saito is an actor best known for his role in the cult-favorite action-comedy film "Scott Pilgrim vs. the World."
  • 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_69e0b4ba6ae88190af871e1f9522c704 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6aa1bea1c81908b85f38b2a471285 completed April 20, 2026, 10:35 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0c0abaf1088190a67d04a4a2482225 completed May 19, 2026, 7:01 a.m.
NEDg Description generation batch_6a0c0b5c43748190b209e13ce8aa0bdb completed May 19, 2026, 7:03 a.m.
NED2 Entity disambiguation (via description) batch_6a0c0bb05de481909b343f4105e5f4cc completed May 19, 2026, 7:05 a.m.
Created at: April 16, 2026, 11:40 a.m.