Triple

T15293901
Position Surface form Disambiguated ID Type / Status
Subject Going Hollywood E365601 entity
Predicate hasCastMember P2308 FINISHED
Object Fifi D'Orsay E751227 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: Fifi D'Orsay | Statement: [Going Hollywood, hasCastMember, Fifi D'Orsay]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Fifi D'Orsay
Context triple: [Going Hollywood, hasCastMember, Fifi D'Orsay]
  • A. Fifi D'Orsay chosen
    Fifi D'Orsay was a French-Canadian actress and singer known for her vivacious "French vamp" persona in Hollywood films of the late 1920s and 1930s.
  • B. Renée Adorée
    Renée Adorée was a French-born silent film actress best known for her acclaimed role in the World War I drama "The Big Parade" (1925).
  • C. Gisèle
    Gisèle is a feminine given name of French origin, commonly used in Francophone countries and beyond.
  • D. Fifi La Fume
    Fifi La Fume is a skunk cartoon character from Tiny Toon Adventures, known for her romantic obsession with love and her parody of Pepé Le Pew.
  • E. Ninon Dolbin
    Ninon Dolbin was the second wife of German-Swiss writer Hermann Hesse, known for supporting and managing aspects of his literary life.
  • 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_69d85a103d9081908c1ea6c4c73ac8e3 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03682ea488190ac82fdbd0e855d34 completed April 16, 2026, 1:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69fef899e55c8190b1c26491bf37967a completed May 9, 2026, 9:04 a.m.
Created at: April 10, 2026, 3:15 a.m.