Triple

T22844281
Position Surface form Disambiguated ID Type / Status
Subject Genesis E566170 entity
Predicate hasVariant P455 FINISHED
Object Génesis 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: Génesis | Statement: [Genesis, hasVariant, Génesis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Génesis
Context triple: [Genesis, hasVariant, Génesis]
  • A. Genesi
    Genesi is a computer hardware company best known for designing and producing the Pegasos line of PowerPC-based motherboards and systems.
  • B. Genèse
    Genèse is a philosophical work by Michel Serres that explores the themes of origin, chaos, and the emergence of order in nature and human thought.
  • C. Book of Genesis chosen
    The Book of Genesis is the first book of the Hebrew Bible and the Christian Old Testament, narrating the creation of the world, the early history of humanity, and the origins of the people of Israel.
  • D. Genesis 1
    Genesis 1 is the opening chapter of the Bible that narrates the six-day creation of the world by God, forming the foundational Judeo-Christian account of cosmic origins.
  • E. Livro da Criação
    Livro da Criação is an experimental, participatory artist’s book by Brazilian neo-concretist Lygia Pape that invites readers to manipulate abstract forms and colors to explore the process of creation.
  • 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_69e245869e188190a196584f36e682da completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17e8726d4819095b4d999b4172ff7 completed April 29, 2026, 3:44 a.m.
Created at: April 17, 2026, 3:36 p.m.