Triple

T15947676
Position Surface form Disambiguated ID Type / Status
Subject Ann Eilbeck Mason E386726 entity
Predicate name P16 FINISHED
Object Ann Eilbeck Mason 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: Ann Eilbeck Mason | Statement: [Ann Eilbeck Mason, name, Ann Eilbeck Mason]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ann Eilbeck Mason
Context triple: [Ann Eilbeck Mason, name, Ann Eilbeck Mason]
  • A. Ann Eilbeck Mason chosen
    Ann Eilbeck Mason was the wife of American Founding Father George Mason and the matriarch of a prominent Virginia planter family in the 18th century.
  • B. Sarah Y. Mason
    Sarah Y. Mason was an American screenwriter best known for her influential adaptations of classic literature during Hollywood’s early sound era.
  • C. Anne Mason
    Anne Mason is the daughter of Sir Joseph Mason, a character in Anthony Trollope’s novel "Orley Farm."
  • D. Elizabeth Sinskey
    Elizabeth Sinskey is a fictional World Health Organization director and geneticist who plays a central role in Dan Brown’s thriller novel "Inferno."
  • E. Margaret Lindauer
    Margaret Lindauer is an individual notable enough to be recognized as a prominent bearer of the surname Lindauer.
  • 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_69d86da882448190a82ea962fe343b79 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e156d2fda8819085279d2a0f8a02ab completed April 16, 2026, 9:38 p.m.
Created at: April 10, 2026, 4:53 a.m.