Triple

T23226842
Position Surface form Disambiguated ID Type / Status
Subject Little Nellie Kelly E581037 entity
Predicate starring P1507 FINISHED
Object Charles Winninger 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: Charles Winninger | Statement: [Little Nellie Kelly, starring, Charles Winninger]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Charles Winninger
Context triple: [Little Nellie Kelly, starring, Charles Winninger]
  • A. Charles Winninger chosen
    Charles Winninger was an American character actor best known for his comedic and paternal roles in early 20th-century stage and Hollywood films.
  • B. Joseph Weishaar
    Joseph Weishaar is an American architect and designer best known for winning the competition to create the National World War I Memorial in Washington, D.C.
  • C. Knowle Rohrer
    Knowle Rohrer is a recurring antagonist and shadowy government operative in the science-fiction television series "The X-Files."
  • D. Mel Winkler
    Mel Winkler was an American character actor best known for his distinctive voice work in video games and animation, as well as supporting roles in film and television.
  • E. James Scheffer
    James Scheffer, better known as Jim Jonsin, is an American record producer and songwriter recognized for crafting hit tracks across hip hop and pop music.
  • 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_69e246043c48819089bae72c9a9c306c completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f1922f5b4081908145d66ea7534493 completed April 29, 2026, 5:07 a.m.
Created at: April 17, 2026, 4:09 p.m.