Triple

T17436377
Position Surface form Disambiguated ID Type / Status
Subject Ran E424010 entity
Predicate starring P1507 FINISHED
Object Mieko Harada 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: Mieko Harada | Statement: [Ran, starring, Mieko Harada]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mieko Harada
Context triple: [Ran, starring, Mieko Harada]
  • A. Mieko Harada chosen
    Mieko Harada is a Japanese actress best known internationally for her intense portrayal of Lady Kaede in Akira Kurosawa’s epic film "Ran."
  • B. Makiko Tanaka
    Makiko Tanaka is a Japanese politician and former foreign minister, known as the outspoken daughter of influential former Prime Minister Kakuei Tanaka.
  • C. Takako Ohta
    Takako Ohta is a Japanese singer and actress best known for her 1980s idol career and hit songs in the J-pop genre.
  • D. Kumiko Hirano
    Kumiko Hirano is a Japanese individual notable enough to be specifically cited as a bearer of the surname Hirano.
  • E. Takako Konishi
    Takako Konishi was a Japanese office worker whose mysterious death in Minnesota in 2001 inspired the urban legend that she had traveled there searching for the fictional buried money from the film "Fargo."
  • 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.