Triple

T20901023
Position Surface form Disambiguated ID Type / Status
Subject Justice League Dark (film) E514666 entity
Predicate voiceActor P1507 FINISHED
Object Roger Cross 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: Roger Cross | Statement: [Justice League Dark (film), voiceActor, Roger Cross]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roger Cross
Context triple: [Justice League Dark (film), voiceActor, Roger Cross]
  • A. Roger Cross chosen
    Roger Cross is a Canadian actor known for prominent roles in science fiction and action television series, including major parts in shows like 24 and Continuum.
  • B. Robert Cross
    Robert Cross is a relatively common personal name that may refer to multiple individuals across various fields rather than a single widely recognized figure.
  • C. John Walter Cross
    John Walter Cross was an English banker and literary figure best known as the husband and later biographer of the novelist George Eliot.
  • D. Philip Cross
    Philip Cross is a controversial Wikipedia editor known for his extensive and often disputed edits to political and media-related articles.
  • E. David C. Cross
    David C. Cross was a prominent figure in Arkansas history for whom Cross County was named, likely due to his significant local influence or public service.
  • 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_69e0b4f8a1108190bce3d31331290ced completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6e8fc5d488190b62f51c35e768d38 completed April 21, 2026, 3:03 a.m.
Created at: April 16, 2026, 12:47 p.m.