Triple

T19137941
Position Surface form Disambiguated ID Type / Status
Subject The Address Book E468480 entity
Predicate author P4 FINISHED
Object Sophie Calle 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: Sophie Calle | Statement: [The Address Book, author, Sophie Calle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sophie Calle
Context triple: [The Address Book, author, Sophie Calle]
  • A. Sophie Calle chosen
    Sophie Calle is a French conceptual artist and writer known for her investigative, narrative-driven works that blend photography, text, and performance to explore themes of intimacy, surveillance, and identity.
  • B. Marianne Devidel
    Marianne Devidel was the wife of renowned German neoclassical sculptor Johann Gottfried Schadow.
  • C. Laurie Simmons
    Laurie Simmons is an American artist and photographer known for her staged photographs featuring dolls and miniature scenes that explore themes of domesticity, gender roles, and identity.
  • D. Geneviève Gilot
    Geneviève Gilot is a French painter and author best known for her long relationship with Pablo Picasso and her own distinguished career in modern art.
  • E. Sarah Charlesworth
    Sarah Charlesworth was an influential American conceptual artist and photographer associated with the Pictures Generation, known for her critical exploration of mass media imagery and representation.
  • 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_69d8dd0796a48190b34ce4cd9d3f3be5 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e3ee8b988190914ef21ca1b890c6 completed April 20, 2026, 8:29 a.m.
Created at: April 10, 2026, 12:05 p.m.