Triple

T8156140
Position Surface form Disambiguated ID Type / Status
Subject Page Eight E190453 entity
Predicate castMember P1668 FINISHED
Object Marthe Keller E213946 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: Marthe Keller | Statement: [Page Eight, castMember, Marthe Keller]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marthe Keller
Context triple: [Page Eight, castMember, Marthe Keller]
  • A. Marthe Keller chosen
    Marthe Keller is a Swiss actress and former opera director known for her international film career, including prominent roles in 1970s Hollywood thrillers and European cinema.
  • B. Marthe
    Marthe is a feminine given name, commonly used in French and other European languages, that is a variant of the name Martha.
  • C. Marie Pillet
    Marie Pillet was a French actress and activist, best known to many as the mother of filmmaker and actress Julie Delpy.
  • D. Marguerite Gaudelet
    Marguerite Gaudelet was the wife of French civil engineer Gustave Eiffel, famed designer of the Eiffel Tower.
  • E. Marguerite Duthuit
    Marguerite Duthuit was a French woman best known as the daughter of painter Henri Matisse and the wife of art critic Georges Duthuit, placing her at the center of early 20th-century avant-garde artistic circles.
  • 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_69ca82bfeb6481909d07b91b5cf69f59 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb44d8a37481909397b5cc321b94be completed March 31, 2026, 3:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69ccbf18c30c8190bdd98c4f0c2d28ea completed April 1, 2026, 6:45 a.m.
Created at: March 30, 2026, 5:37 p.m.