Triple

T2245193
Position Surface form Disambiguated ID Type / Status
Subject Ilsa Lund E49486 entity
Predicate givenName P17 FINISHED
Object Ilsa E49486 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: Ilsa | Statement: [Ilsa Lund, givenName, Ilsa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ilsa
Context triple: [Ilsa Lund, givenName, Ilsa]
  • A. Ilsa Lund chosen
    Ilsa Lund is the enigmatic former lover of Rick Blaine and the central female protagonist in the classic 1942 film "Casablanca," portrayed by Ingrid Bergman.
  • B. Brigitte
    Brigitte is a French former teacher best known as the wife of Emmanuel Macron, the President of France.
  • C. Malena
    Malena is a feminine given name, commonly used in various cultures and often considered a diminutive or variant of names like Magdalena.
  • D. Marlene
    Marlene is a German biographical film directed by Joseph Vilsmaier about the life and career of actress and singer Marlene Dietrich.
  • E. Dorothee
    Dorothee is a feminine given name, commonly used in German- and French-speaking countries, that is a variant of the name Dorothea.
  • 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_69a88aa979788190ad6500f1d8eee2fc completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc0e8d5648190915ff689c7ca42bc completed March 7, 2026, 6:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae71c1edd081909acbb8b1915ce0d6 completed March 9, 2026, 7:07 a.m.
Created at: March 4, 2026, 7:47 p.m.