Triple

T18856704
Position Surface form Disambiguated ID Type / Status
Subject Audrey Reede E461188 entity
Predicate partOf P40 FINISHED
Object Liar Liar franchise 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: Liar Liar franchise | Statement: [Audrey Reede, partOf, Liar Liar franchise]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Liar Liar franchise
Context triple: [Audrey Reede, partOf, Liar Liar franchise]
  • A. Liar Liar chosen
    Liar Liar is a 1997 comedy film starring Jim Carrey as a fast-talking lawyer magically compelled to tell the truth for 24 hours, leading to a series of chaotic and humorous consequences.
  • B. Liar Liar
    "Liar Liar" is a pop song by American singer Christina Grimmie that showcases her powerful vocals and emotive, piano-driven style.
  • C. Regan Reilly series
    The Regan Reilly series is a collection of lighthearted mystery novels featuring a savvy female private investigator, written by American author Carol Higgins Clark.
  • D. Hollywood Liar
    "Hollywood Liar" is a song featured on the album *Inside Story*, likely characterized by themes of deception and the darker side of fame.
  • E. Rogue Lawyer
    Rogue Lawyer is a legal thriller novel by John Grisham that follows an unconventional street lawyer who takes on dangerous and morally complex cases.
  • 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_69d8dcfb7b9c8190854e7b171b98ea2e completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5c05d0bb8819094d0447441f85b57 completed April 20, 2026, 5:57 a.m.
Created at: April 10, 2026, 11:57 a.m.