Triple

T12668953
Position Surface form Disambiguated ID Type / Status
Subject Marina Sirtis E302626 entity
Predicate voiceRole P12691 FINISHED
Object Demona in Gargoyles E945887 NE FINISHED

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: Demona in Gargoyles | Statement: [Marina Sirtis, voiceRole, Demona in Gargoyles]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Demona in Gargoyles
Context triple: [Marina Sirtis, voiceRole, Demona in Gargoyles]
  • A. Demona chosen
    Demona is a central antagonist in Disney's animated series "Gargoyles," a powerful and vengeful gargoyle who harbors a deep hatred for humans.
  • B. Raven Darkhölme
    Raven Darkhölme, better known as Mystique, is a blue-skinned, shape-shifting mutant and frequent antihero in Marvel's X-Men universe.
  • C. Wanda the werewolf
    Wanda the werewolf is a friendly, maternal werewolf character from the Hotel Transylvania film series and one of Mavis Dracula’s closest companions.
  • D. Raven
    Raven is a component or section within the work "The Art of Doing Nothing," likely contributing a distinct thematic or narrative element to the overall piece.
  • E. Raven
    Raven is the surname of American botanist and environmentalist Peter H. Raven, renowned for his work in plant systematics and biodiversity conservation.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d7bded71a88190bb76e2413af9ea66 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96183a6048190b2ef219eb9d20aa4 completed April 10, 2026, 8:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6688e101481909bc3b9e13ed84632 completed May 2, 2026, 9:11 p.m.
Created at: April 9, 2026, 5:20 p.m.