Triple

T17436376
Position Surface form Disambiguated ID Type / Status
Subject Ran E424010 entity
Predicate starring P1507 FINISHED
Object Daisuke Ryū NE NERFINISHED

How this triple was built (2 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: Daisuke Ryū | Statement: [Ran, starring, Daisuke Ryū]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Daisuke Ryū
Context triple: [Ran, starring, Daisuke Ryū]
  • A. Daisuke Ryū chosen
    Daisuke Ryū is a Japanese actor best known for his roles in Akira Kurosawa’s historical epics and other period films.
  • B. Kenichi
    Kenichi is a Japanese masculine given name commonly used for boys and men in Japan.
  • C. Ryūō
    Ryūō is a town in Shiga Prefecture, Japan, known for its location near Lake Biwa and its blend of rural landscapes with growing commercial development.
  • D. Kyuji Fujikawa
    Kyuji Fujikawa is a Japanese professional baseball pitcher best known as a dominant closer in Nippon Professional Baseball and a longtime star for the Hanshin Tigers.
  • E. Takamura Kengo
    Takamura Kengo is a Japanese architect known for his work on the historic Imperial Hotel in Tokyo.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d889d88b6081908bada047f5b3ba51 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4490426008190b474ed76aca5d6f3 completed April 19, 2026, 3:16 a.m.
Created at: April 10, 2026, 5:46 a.m.