Triple

T35440954
Position Surface form Disambiguated ID Type / Status
Subject Barefoot Gen (TV drama) E1024336 entity
Predicate workOriginAuthorBackground P116030 FINISHED
Object Keiji Nakazawa was a Hiroshima bombing survivor 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: Keiji Nakazawa was a Hiroshima bombing survivor | Statement: [Barefoot Gen (TV drama), workOriginAuthorBackground, Keiji Nakazawa was a Hiroshima bombing survivor]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: workOriginAuthorBackground
Context triple: [Barefoot Gen (TV drama), workOriginAuthorBackground, Keiji Nakazawa was a Hiroshima bombing survivor]
  • A. authorOrigin
    Indicates that an author has a specific place, region, or country as their origin or background.
  • B. hasAuthorBackgroundIn
    Indicates that an author possesses a particular background, such as education, experience, or expertise, in a specified field or domain.
  • C. coAuthorBackground
    Indicates that two or more entities share a professional or biographical context related to their joint authorship of a work.
  • D. originAuthor
    Indicates that an entity is the original creator or author of another entity (such as a work, document, or idea).
  • E. hasAuthorialBackground chosen
    Indicates that an entity has a creator or author with a specific background, context, or set of characteristics associated with them.
  • F. None of above.

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_69f76df8089481909f0018266ee881b7 completed May 3, 2026, 3:47 p.m.
NER Named-entity recognition batch_69f79da9f80c8190b0afd8509f28747b completed May 3, 2026, 7:10 p.m.
PD Predicate disambiguation batch_69f79617d40481909ba372f94209c08b completed May 3, 2026, 6:38 p.m.
Created at: May 3, 2026, 4:04 p.m.