Triple

T7101871
Position Surface form Disambiguated ID Type / Status
Subject María Kodama E165477 entity
Predicate name P16 FINISHED
Object María Kodama E165477 NE FINISHED

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: María Kodama | Statement: [María Kodama, name, María Kodama]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: María Kodama
Context triple: [María Kodama, name, María Kodama]
  • A. María Kodama chosen
    María Kodama was an Argentine writer, translator, and literary figure best known as the close collaborator, heir, and later widow of Jorge Luis Borges.
  • B. Michiko Shōda
    Michiko Shōda, later Empress Michiko, is the former Empress consort of Japan and the first commoner to marry into the Japanese imperial family.
  • C. Fumiko Shōda
    Fumiko Shōda was a Japanese woman best known as the mother of Michiko Shōda, who became Empress Michiko of Japan.
  • 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. Tatsuko Kawashima
    Tatsuko Kawashima is the maternal grandmother of Prince Hisahito of Akishino and a member of the extended Japanese imperial family through her daughter, Princess Kiko.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69c6887fcddc8190a5d58908f6dee590 completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e588aee08190bfb3d96135c0a322 completed March 27, 2026, 8:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8a1f8da648190987fad6e37620cef completed March 29, 2026, 3:52 a.m.
Created at: March 27, 2026, 2:42 p.m.