Triple

T20949635
Position Surface form Disambiguated ID Type / Status
Subject Batman: Year One (film) E515943 entity
Predicate featuresVoiceActor P39669 FINISHED
Object Liliana Mumy 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: Liliana Mumy | Statement: [Batman: Year One (film), featuresVoiceActor, Liliana Mumy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Liliana Mumy
Context triple: [Batman: Year One (film), featuresVoiceActor, Liliana Mumy]
  • A. Liliana Mumy chosen
    Liliana Mumy is an American actress and voice actress known for her roles in family films and animated television series such as "Cheaper by the Dozen" and "The Loud House."
  • B. Irina Malandina
    Irina Malandina is a former Russian flight attendant best known as the ex-wife of billionaire businessman and former Chelsea F.C. owner Roman Abramovich.
  • C. Miriam Svet
    Miriam Svet was the wife of American film producer and studio executive Dore Schary.
  • D. Tatiana Javorsky
    Tatiana Javorsky was the wife of American broadcast journalist Charles Collingwood.
  • E. Tamara Muro
    Tamara Muro is a business associate of Christine Baumgartner, known in connection with Baumgartner’s professional ventures.
  • 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_69e0b4fcd678819087a304291f14330a completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fadc08148190b4ff710f94462a26 completed April 21, 2026, 4:19 a.m.
Created at: April 16, 2026, 1:18 p.m.