Triple

T18163554
Position Surface form Disambiguated ID Type / Status
Subject Marion Fairfax E434828 entity
Predicate name P16 FINISHED
Object Marion Fairfax 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: Marion Fairfax | Statement: [Marion Fairfax, name, Marion Fairfax]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marion Fairfax
Context triple: [Marion Fairfax, name, Marion Fairfax]
  • A. Marion Fairfax chosen
    Marion Fairfax was an early 20th-century American screenwriter and playwright known for her work on major silent films and adaptations.
  • B. Rebecca Tayloe
    Rebecca Tayloe was a Virginia plantation heiress who became the wife of American Founding Father and Declaration of Independence signer Francis Lightfoot Lee.
  • C. Marion Stirling
    Marion Stirling was an American archaeologist and researcher known for her work alongside her husband Matthew Stirling in the study of ancient Mesoamerican civilizations.
  • D. Marion Livingston
    Marion Livingston was a Scottish noblewoman of the influential Livingston family of Callendar in the late medieval period.
  • E. Elizabeth Tyree
    Elizabeth Tyree was an American stage actress and philanthropist known for her leadership in organizing theatrical community support efforts during World War I.
  • 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_69d8b90b7a188190b3fc7b8d4a6cd20a completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4dec419788190a999a68f32fab39b completed April 19, 2026, 1:55 p.m.
Created at: April 10, 2026, 10:30 a.m.