Triple

T21992016
Position Surface form Disambiguated ID Type / Status
Subject Annabel Banks E543112 entity
Predicate givenName P17 FINISHED
Object Annabel 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: Annabel | Statement: [Annabel Banks, givenName, Annabel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Annabel
Context triple: [Annabel Banks, givenName, Annabel]
  • A. Annabel chosen
    Annabel is a feminine given name of Latin origin, commonly interpreted to mean "lovable" or "graceful."
  • B. Annabel
    Annabel is a character from the animated conspiracy-comedy series "Inside Job," known for her role in the show's satirical take on shadow governments and secret organizations.
  • C. Annabel Bleach
    Annabel Bleach is a musician best known as a member of the Australian indie pop band The Cannanes.
  • D. Annabel Clare Daldry
    Annabel Clare Daldry is the daughter of British theatre and film director Stephen Daldry.
  • E. Maud
    Maud was a Norwegian polar exploration ship used by Roald Amundsen during his Arctic expeditions in the early 20th century.
  • 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_69e0c48136b081908831fa907cc02e18 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1270e951081908deda039b47ca84b completed April 28, 2026, 9:30 p.m.
Created at: April 16, 2026, 8:05 p.m.