Triple

T18971678
Position Surface form Disambiguated ID Type / Status
Subject Princess Chichibu E464184 entity
Predicate birthName P65 FINISHED
Object Setsuko Matsudaira 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: Setsuko Matsudaira | Statement: [Princess Chichibu, birthName, Setsuko Matsudaira]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Setsuko Matsudaira
Context triple: [Princess Chichibu, birthName, Setsuko Matsudaira]
  • A. Setsuko Matsudaira chosen
    Setsuko Matsudaira was a Japanese princess and member of the imperial family as the wife of Prince Chichibu, Emperor Hirohito’s younger brother.
  • B. Setsuko Ideta
    Setsuko Ideta is a Japanese artist and model best known as the wife and muse of the painter Balthus, with whom she helped preserve and promote his artistic legacy.
  • C. Shigeko Sasaki
    Shigeko Sasaki is a Japanese individual known primarily for sharing the given name Shigeko, though specific widely recognized public achievements or roles under this name are not well documented.
  • D. Yoshiko Ikeda
    Yoshiko Ikeda was the wife of former Japanese Prime Minister Hayato Ikeda and served as Japan’s First Lady during his tenure in the early 1960s.
  • E. Shigeko Hirano
    Shigeko Hirano is a Japanese voice actress known for her work in anime and related media.
  • 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_69d8dd008af48190a97ff1c6488edf1b completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d61a8bbc8190881908a71e0f2a53 completed April 20, 2026, 7:30 a.m.
Created at: April 10, 2026, noon