Triple

T6559622
Position Surface form Disambiguated ID Type / Status
Subject Virginia Katherine McMath E152543 entity
Predicate notableWork P4 FINISHED
Object Kitty Foyle E57916 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: Kitty Foyle | Statement: [Virginia Katherine McMath, notableWork, Kitty Foyle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kitty Foyle
Context triple: [Virginia Katherine McMath, notableWork, Kitty Foyle]
  • A. Kitty Foyle chosen
    Kitty Foyle is a 1940 romantic drama film best known for Ginger Rogers’ Oscar-winning performance as a working-class woman navigating love and social class.
  • B. Sadie Miller
    Sadie Miller is a British actress and writer, best known for continuing her mother Elisabeth Sladen’s legacy by voicing Sarah Jane Smith in Doctor Who audio dramas.
  • C. Mrs. Brill
    Mrs. Brill is the Banks family's cook and housekeeper in the "Mary Poppins" stories.
  • D. Hildy
    Hildy is a brash, fast-talking New York City taxi driver and one of the central comic female leads in the musical "On the Town."
  • E. La Doyenne
    La Doyenne is the traditional nickname of Liège–Bastogne–Liège, one of cycling’s oldest and most prestigious one-day Classics.
  • 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_69c688058d6881908c19b309cc55dbfa completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6ae22442081909bd6e2ba0091c56b completed March 27, 2026, 4:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6cb8bae88819089cff70fa1101a39 completed March 27, 2026, 6:25 p.m.
Created at: March 27, 2026, 1:52 p.m.