Triple

T10288157
Position Surface form Disambiguated ID Type / Status
Subject Martta E241287 entity
Predicate relatedName P3889 FINISHED
Object Marthe E241286 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 | Statement: [Martta, relatedName, Marthe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marthe
Context triple: [Martta, relatedName, Marthe]
  • A. Marthe chosen
    Marthe is a feminine given name, commonly used in French and other European languages, that is a variant of the name Martha.
  • B. Marthe Keller
    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.
  • C. Marthe Rougon
    Marthe Rougon is a central character in Émile Zola’s Rougon-Macquart series, depicted as a devout yet psychologically fragile woman whose religious fervor and inner turmoil drive much of the drama in "La Conquête de Plassans."
  • D. Marguerite Courtot
    Marguerite Courtot was an American silent film actress known for her work in early 20th-century cinema, particularly in serials and adventure films.
  • E. Marthe Poncin
    Marthe Poncin was a film editor known for her work on French cinema, including editing the classic film "Hôtel du Nord."
  • 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_69d381aaafc08190af475ef58dc16aba completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d2b9d76c8190b1ef6ecf4c1a2a09 completed April 7, 2026, 9:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69d6f8556f4081908390bc5c14dcf560 completed April 9, 2026, 12:52 a.m.
Created at: April 6, 2026, 11:41 a.m.