Triple

T19973499
Position Surface form Disambiguated ID Type / Status
Subject Roger E493626 entity
Predicate workStars P94797 FINISHED
Object Mary Wickes 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: Mary Wickes | Statement: [Roger, workStars, Mary Wickes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Wickes
Context triple: [Roger, workStars, Mary Wickes]
  • A. Mary Wickes chosen
    Mary Wickes was an American character actress known for her sharp-tongued, comedic roles in film and television across several decades.
  • B. Marion Hutton
    Marion Hutton was an American singer and actress best known as a featured vocalist with the Glenn Miller Orchestra during the big band era.
  • C. Maud Ellen Dixon
    Maud Ellen Dixon was the wife of New Zealand physicist and science administrator Ernest Marsden.
  • D. Ella Mae Morse
    Ella Mae Morse was an American singer known for her energetic blend of jazz, pop, and early rock and roll styles during the 1940s and 1950s.
  • E. Marie Alweather
    Marie Alweather is a character from the animated film "Paulie," appearing as part of the story surrounding the talking parrot's adventures.
  • 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_69da626a67648190af9653832a3aeced completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e65bcb72048190aedb4f085ace0493 completed April 20, 2026, 5 p.m.
Created at: April 11, 2026, 3:17 p.m.