Triple

T20383869
Position Surface form Disambiguated ID Type / Status
Subject Tish E497908 entity
Predicate featuresActor P15562 FINISHED
Object Rags Ragland 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: Rags Ragland | Statement: [Tish, featuresActor, Rags Ragland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rags Ragland
Context triple: [Tish, featuresActor, Rags Ragland]
  • A. Rags Ragland chosen
    Rags Ragland was an American character actor and comedian known for his scene-stealing comic roles in 1940s Hollywood films.
  • B. Mary Nix
    Mary Nix was the mother of the noted Welsh philologist William Jones, renowned for his work on Indo-European language relationships.
  • C. Alene Akins
    Alene Akins was an American former airline stewardess best known as the ex-wife of entertainer Wayne Newton, whom she married and divorced twice.
  • D. Alene Akins
    Alene Akins was a former Playboy Bunny and the on-again, off-again wife of television host Larry King, with whom she had two children.
  • E. Ada Haggett
    Ada Haggett is a central character in the play "The Late Christopher Bean," depicted as a modest, hardworking maid whose unassuming nature contrasts with the greed and pretensions of the household she serves.
  • 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_69e0b4a5b7908190a972e4e7e698ae94 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e678b2ceec819091ad5205ee9b2174 completed April 20, 2026, 7:04 p.m.
Created at: April 16, 2026, 11:27 a.m.