Triple

T2061005
Position Surface form Disambiguated ID Type / Status
Subject Lisa Kron E45788 entity
Predicate name P16 FINISHED
Object Lisa Kron E45788 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: Lisa Kron | Statement: [Lisa Kron, name, Lisa Kron]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lisa Kron
Context triple: [Lisa Kron, name, Lisa Kron]
  • A. Lisa Kron chosen
    Lisa Kron is an American playwright and performer best known for her Tony Award–winning work on the musical "Fun Home" and her incisive, often autobiographical plays exploring identity, family, and social issues.
  • B. Ann Rork
    Ann Rork was an American silent film actress and socialite best known for her roles in 1920s cinema and her later marriage to oil tycoon J. Paul Getty.
  • C. Aimee Mann
    Aimee Mann is an American singer-songwriter and bassist known for her introspective lyrics, melodic pop-rock style, and acclaimed work on the "Magnolia" film soundtrack.
  • D. Joanna Newsom
    Joanna Newsom is an American singer-songwriter and harpist known for her intricate compositions, poetic lyrics, and distinctive vocal style.
  • E. Mary Lou Jepsen
    Mary Lou Jepsen is an American engineer, inventor, and entrepreneur known for her pioneering work in display technology and for co-founding the low-cost computing initiative One Laptop per Child.
  • 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_69a8891a19508190a12ef1e192308dcb completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abb9d0ecf08190aec20338a6ba9911 completed March 7, 2026, 5:38 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae271cb26c81908664f4c26f4fb5ea completed March 9, 2026, 1:49 a.m.
Created at: March 4, 2026, 7:40 p.m.