Triple

T16256977
Position Surface form Disambiguated ID Type / Status
Subject The Mirror Has Two Faces E394655 entity
Predicate starring P1507 FINISHED
Object Mimi Rogers 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: Mimi Rogers | Statement: [The Mirror Has Two Faces, starring, Mimi Rogers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mimi Rogers
Context triple: [The Mirror Has Two Faces, starring, Mimi Rogers]
  • A. Mimi Rogers chosen
    Mimi Rogers is an American actress and former model known for her work in film and television since the 1980s, including notable roles in movies like "The Rapture" and "Austin Powers: International Man of Mystery."
  • B. Mimi Thompson
    Mimi Thompson is the wife of American pop artist James Rosenquist.
  • C. Melissa Robinson
    Melissa Robinson is a key supporting character in the comedy film "Ace Ventura: Pet Detective," serving as a competent and skeptical ally to the eccentric detective Ace Ventura.
  • D. Lisa Gottsegen
    Lisa Gottsegen is an American businesswoman and philanthropist best known as the longtime wife of actor Dustin Hoffman.
  • E. Melissa Loya
    Melissa Loya is known as the wife of Episcopal bishop Craig Loya.
  • 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_69d87f221d8081909b0b2063e7528ba2 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e2459b1624819086bf681075097235 completed April 17, 2026, 2:37 p.m.
Created at: April 10, 2026, 5:04 a.m.