Triple

T19024546
Position Surface form Disambiguated ID Type / Status
Subject Brief Encounter E465573 entity
Predicate characterPortrayed P1507 FINISHED
Object Celia Johnson as Laura Jesson 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: Celia Johnson as Laura Jesson | Statement: [Brief Encounter, characterPortrayed, Celia Johnson as Laura Jesson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Celia Johnson as Laura Jesson
Context triple: [Brief Encounter, characterPortrayed, Celia Johnson as Laura Jesson]
  • A. Joanna Gilliat
    Joanna Gilliat is known primarily as the daughter of British screenwriter and film director Sidney Gilliat.
  • B. Celia Johnson chosen
    Celia Johnson was a distinguished English actress best known for her nuanced, understated performances in classic British films such as "Brief Encounter."
  • C. Eileen Le Mesurier
    Eileen Le Mesurier was the mother of British journalist and spy Jeremy Wolfenden, connected to mid-20th-century British intellectual and diplomatic circles.
  • D. Leslie Maitland
    Leslie Maitland is a Canadian film and television producer known for her work on various acclaimed screen projects.
  • E. Marjorie Lloyd
    Marjorie Lloyd is a woman known primarily as the sister of Gloria Lloyd.
  • 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_69d8dd025c188190a1d81f5b4ec7e2c6 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d6e166088190937ef19739437f7c completed April 20, 2026, 7:33 a.m.
Created at: April 10, 2026, 12:02 p.m.