Triple

T18241117
Position Surface form Disambiguated ID Type / Status
Subject Priscilla Moran E436811 entity
Predicate name P16 FINISHED
Object Priscilla Moran 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: Priscilla Moran | Statement: [Priscilla Moran, name, Priscilla Moran]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Priscilla Moran
Context triple: [Priscilla Moran, name, Priscilla Moran]
  • A. Priscilla Moran chosen
    Priscilla Moran was an American child actress of the silent film era, known for her roles in early 1920s cinema.
  • B. Priscilla Little
    Priscilla Little is a member of the Little family, which includes Janna Little Ryan, the wife of former U.S. Speaker of the House Paul Ryan.
  • C. Priscilla Anne Mack
    Priscilla Anne Mack is the wife of former U.S. Senator Connie Mack III and a member of the prominent Mack political family.
  • D. Priscilla Lloyd
    Priscilla Lloyd was the mother of Scottish bishop and educator Charles Wordsworth, connecting her to a prominent 19th-century ecclesiastical and academic family.
  • E. Priscilla Buckley
    Priscilla Buckley was an American journalist and longtime managing editor of the conservative magazine National Review.
  • 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_69d8b91104e08190a8241f7d260a5162 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4f7e287548190b666a990e5b168b0 completed April 19, 2026, 3:42 p.m.
Created at: April 10, 2026, 10:33 a.m.