Triple

T18177064
Position Surface form Disambiguated ID Type / Status
Subject The Betty White Show E435189 entity
Predicate hasCastMember P2308 FINISHED
Object Georgia Engel 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: Georgia Engel | Statement: [The Betty White Show, hasCastMember, Georgia Engel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Georgia Engel
Context triple: [The Betty White Show, hasCastMember, Georgia Engel]
  • A. Georgia Engel chosen
    Georgia Engel was an American actress best known for her soft-spoken, sweetly quirky roles in television comedies such as "The Mary Tyler Moore Show" and "Everybody Loves Raymond."
  • B. Eve McClure
    Eve McClure was an American artist and the third wife of writer Henry Miller, known for her influence on his life and work during the 1940s.
  • C. Didi Conn
    Didi Conn is an American actress best known for her role as the bubbly, high-voiced Frenchy in the classic film musical "Grease."
  • D. Wynonie Harris
    Wynonie Harris was an influential American blues and R&B singer whose energetic performances and hit records in the 1940s and 1950s helped shape the development of rock and roll.
  • E. Molly Messick
    Molly Messick is an American audio producer and journalist known for her work in public radio and podcasting.
  • 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_69d8b90c7ec081909b4694ccecb449c6 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4df5a72008190bd2e56205b995a87 completed April 19, 2026, 1:57 p.m.
Created at: April 10, 2026, 10:31 a.m.