Triple

T38611552
Position Surface form Disambiguated ID Type / Status
Subject Henri Charrière E934494 entity
Predicate autobiographicalSubject P58275 FINISHED
Object his imprisonment in French Guiana LITERAL 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: his imprisonment in French Guiana | Statement: [Henri Charrière, autobiographicalSubject, his imprisonment in French Guiana]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: autobiographicalSubject
Context triple: [Henri Charrière, autobiographicalSubject, his imprisonment in French Guiana]
  • A. hasAutobiographicalSubject chosen
    Indicates that something (such as a work, text, or narrative) has a subject that is the author or creator’s own life or personal experiences.
  • B. wroteAutobiographicalWork
    Indicates that a person is the author of a written work that is an account of their own life.
  • C. memoirAuthor
    Indicates that one entity is the author or writer of the other entity, which is a memoir.
  • D. biographicalSubjectTitle
    Indicates that a title or role is used as the biographical subject of a work or biographical description.
  • E. hasBiographicalSubjectRole
    Indicates that a role is the biographical subject of a biographical work or account.
  • 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_69f76eccd6d081909ccce171011739a1 completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_69fcdb0de8c08190928cd1323f80ab5c completed May 7, 2026, 6:33 p.m.
PD Predicate disambiguation batch_69fcd9017dd88190b32a73fe78909740 completed May 7, 2026, 6:25 p.m.
Created at: May 3, 2026, 4:32 p.m.