Triple

T21463385
Position Surface form Disambiguated ID Type / Status
Subject Up the Junction E529529 entity
Predicate starring P1507 FINISHED
Object Carol White 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: Carol White | Statement: [Up the Junction, starring, Carol White]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carol White
Context triple: [Up the Junction, starring, Carol White]
  • A. Carol White chosen
    Carol White was a British actress best known for her powerful performances in socially conscious films of the 1960s, particularly in the kitchen-sink drama movement.
  • B. Alice White
    Alice White was an American film actress prominent in the late silent and early sound eras of Hollywood cinema.
  • C. Liz White
    Liz White is a British actress best known for her role as WPC Annie Cartwright in the television drama series "Life on Mars."
  • D. Sheila Whiteley
    Sheila Whiteley was a British musicologist renowned for her pioneering work on popular music, gender, and cultural studies.
  • E. Sheila White
    Sheila White was a British actress known for her roles in 1970s film and television comedies.
  • 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_69e0c458133481908ae8b41a12c4edec completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e9e9efdb188190be79b72e1bd18860 completed April 23, 2026, 9:44 a.m.
Created at: April 16, 2026, 6:09 p.m.