Triple

T23561027
Position Surface form Disambiguated ID Type / Status
Subject Karen Walker E579235 entity
Predicate portrayedBy P1507 FINISHED
Object Megan Mullally 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: Megan Mullally | Statement: [Karen Walker, portrayedBy, Megan Mullally]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Megan Mullally
Context triple: [Karen Walker, portrayedBy, Megan Mullally]
  • A. Megan Mullally chosen
    Megan Mullally is an American actress, comedian, and singer best known for her Emmy-winning role as Karen Walker on the television sitcom "Will & Grace."
  • B. Liz Mullally
    Liz Mullally is a musician best known for her past role as a member of the American alternative rock band Blue October.
  • C. Kate Mullally
    Kate Mullally is a person notable enough to be specifically cited as a bearer of the surname Mullally.
  • D. Elizabeth Mitchell
    Elizabeth Mitchell is an American actress known for her roles in television series such as "Lost" and "V," as well as films including "The Purge: Election Year."
  • E. Kristin Davis
    Kristin Davis is an American actress best known for her role as Charlotte York on the television series "Sex and the City" and its related films.
  • 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_69e245fe24588190888f3aec8407d8e3 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f1af680ee88190a23a6f9fed7ae757 completed April 29, 2026, 7:12 a.m.
Created at: April 17, 2026, 6:16 p.m.