Triple

T22797705
Position Surface form Disambiguated ID Type / Status
Subject Arkangel E564293 entity
Predicate mainCharacter P1183 FINISHED
Object Marie Sambrell 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: Marie Sambrell | Statement: [Arkangel, mainCharacter, Marie Sambrell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marie Sambrell
Context triple: [Arkangel, mainCharacter, Marie Sambrell]
  • A. Marie Sambrell chosen
    Marie Sambrell is a character from the "Black Mirror" episode "Arkangel," depicted as an overprotective mother who uses invasive surveillance technology to monitor and control her daughter's life.
  • B. Marie Recio
    Marie Recio was a 19th-century French mezzo-soprano best known as the second wife and close companion of composer Hector Berlioz.
  • C. María Ripoll
    María Ripoll is a Spanish film director known for her work on both Spanish and international films, including the family drama "Tortilla Soup."
  • D. Francisca Subirana
    Francisca Subirana was the wife of Cuban-born inventor, diplomat, and philanthropist Ricardo Wolf.
  • E. Lourdes Faberes
    Lourdes Faberes is a Filipino-British actress known for her work in British television and film, including prominent roles in series like Good Omens and various UK dramas.
  • 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_69e2458185f88190b0045227ee420411 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17cda76448190891c5190e1d75ae0 completed April 29, 2026, 3:36 a.m.
Created at: April 17, 2026, 3:30 p.m.