Triple

T22352561
Position Surface form Disambiguated ID Type / Status
Subject Grace Dover E552569 entity
Predicate hasSibling P363 FINISHED
Object Anna Dover E1500431 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: Anna Dover | Statement: [Grace Dover, hasSibling, Anna Dover]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anna Dover
Context triple: [Grace Dover, hasSibling, Anna Dover]
  • A. Anna Dover chosen
    Anna Dover is the young daughter who goes missing in the 2013 thriller film "Prisoners," driving her father Keller Dover’s desperate search.
  • B. Jane Livesey
    Jane Livesey is best known as the wife of the late English actor Bob Hoskins.
  • C. Jane Sawyer
    Jane Sawyer is a fictional character who serves as the guardian of Rebecca Randall in the classic children’s novel "Rebecca of Sunnybrook Farm."
  • D. Sarah Sawyer
    Sarah Sawyer is a fictional character known as the wife of former FBI agent and security expert Will Sawyer in the action film "Skyscraper."
  • E. Mary Jenkins
    Mary Jenkins is the sharp-witted, hardworking apartment building manager portrayed by Marla Gibbs on the sitcom "227."
  • 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_69e11e4a0ad08190a385b4d343cf6524 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1579cbbe88190bf2f27d34fc8f30e completed April 29, 2026, 12:58 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0ae05c2bd4819086f51f6cb64f59c4 completed May 18, 2026, 9:48 a.m.
Created at: April 16, 2026, 8:44 p.m.