Triple

T23231729
Position Surface form Disambiguated ID Type / Status
Subject Demian E581173 entity
Predicate character P662 FINISHED
Object Frau Eva 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: Frau Eva | Statement: [Demian, character, Frau Eva]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frau Eva
Context triple: [Demian, character, Frau Eva]
  • A. Eva
    Eva is a 1962 psychological drama film directed by Joseph Losey, known for its intense character study and atmospheric European setting.
  • B. Eva chosen
    Eva is a feminine given name of Hebrew origin, equivalent to "Eve" and widely used in many languages and cultures.
  • C. Frau Frieda
    Frau Frieda is a mysterious, dream-haunted woman at the center of Gabriel García Márquez’s short story “I Sell My Dreams,” known for making a living by interpreting and selling her prophetic dreams.
  • D. Frau Frieda
    Frau Frieda is the traditional costumed mascot of the Kitchener-Waterloo Oktoberfest, symbolizing the festival’s German heritage and festive spirit.
  • E. Éva
    Éva is a feminine given name of Hungarian origin, notably borne by the actress Eva Bartok.
  • 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_69e246043c48819089bae72c9a9c306c completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f1923325a08190a529da687de53489 completed April 29, 2026, 5:08 a.m.
Created at: April 17, 2026, 4:09 p.m.