Triple

T23017994
Position Surface form Disambiguated ID Type / Status
Subject The Woman in Green E573084 entity
Predicate starring P1507 FINISHED
Object Paul Cavanagh 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: Paul Cavanagh | Statement: [The Woman in Green, starring, Paul Cavanagh]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paul Cavanagh
Context triple: [The Woman in Green, starring, Paul Cavanagh]
  • A. Paul Cavanagh chosen
    Paul Cavanagh was a British-born film and television actor known for his suave, often aristocratic roles in Hollywood productions from the 1930s through the 1950s.
  • B. Paul Kennerley
    Paul Kennerley is an English singer-songwriter and record producer best known for his country music concept albums and collaborations with Emmylou Harris.
  • C. Paul Deakin
    Paul Deakin is an American drummer best known as a co-founder and longtime member of the country-rock band The Mavericks.
  • D. Paul Callaghan
    Paul Callaghan is a notable individual whose specific prominence may refer to several people sharing the name, including figures in fields such as science, sports, or public service.
  • E. Phil Callaghan
    Phil Callaghan is a person notable enough to be recognized as a bearer of the surname Callaghan.
  • 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_69e245b764cc8190a51be76f1d9611e1 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f183e64a4c8190b8d29ed638c7fef8 completed April 29, 2026, 4:07 a.m.
Created at: April 17, 2026, 3:52 p.m.