Triple

T5085676
Position Surface form Disambiguated ID Type / Status
Subject Valerie E114631 entity
Predicate editor P1954 FINISHED
Object George White E409265 NE FINISHED

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: George White | Statement: [Valerie, editor, George White]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George White
Context triple: [Valerie, editor, George White]
  • A. George White chosen
    George White was a film editor active in mid-20th-century American cinema, known for his work on classic Hollywood productions.
  • B. George White
    George White was a British Army general best known for commanding the garrison during the Siege of Ladysmith in the Second Boer War.
  • C. Joe Williams
    Joe Williams was a renowned American jazz and blues singer best known for his powerful baritone voice and celebrated recordings with the Count Basie Orchestra.
  • D. Jimmy Dorsey
    Jimmy Dorsey was an American jazz clarinetist, saxophonist, composer, and big band leader who became one of the most popular bandleaders of the Swing Era.
  • E. Bert Williams
    Bert Williams was a pioneering African American vaudeville and Broadway comedian, singer, and actor who became one of the most famous and influential entertainers of the early 20th century.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69bd443e941881908eb4e8c685b6f656 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd751db4f4819088b998d7af0e6f41 completed March 20, 2026, 4:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69beb13fd3a88190b5a665ba56fdd455 completed March 21, 2026, 2:54 p.m.
Created at: March 20, 2026, 1:40 p.m.