Triple

T20807750
Position Surface form Disambiguated ID Type / Status
Subject Kitty Vane E512207 entity
Predicate hasLoveInterest P7325 FINISHED
Object Gerald Shannon 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: Gerald Shannon | Statement: [Kitty Vane, hasLoveInterest, Gerald Shannon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gerald Shannon
Context triple: [Kitty Vane, hasLoveInterest, Gerald Shannon]
  • A. Gerald Shannon chosen
    Gerald Shannon is a central character in the 1935 romantic drama film "The Dark Angel," around whom much of the story’s emotional conflict revolves.
  • B. Gerald Geraghty
    Gerald Geraghty was an American screenwriter known for his work on mid-20th-century Western films.
  • C. William Shannon
    William Shannon was an early settler or notable historical figure in British Columbia, Canada, after whom the prominent Shannon Falls near Squamish is named.
  • D. Tony Gillingham
    Tony Gillingham is a wealthy and charming aristocrat in Downton Abbey who becomes one of Lady Mary Crawley’s principal suitors.
  • E. Gerald Hughes
    Gerald Hughes is best known as the brother of British poet Ted Hughes and as a writer and memoirist who documented their family life and Yorkshire upbringing.
  • 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_69e0b4cc69f481908e98751e697b9df4 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c2d0a2a081908fb0e3d890e87aaf completed April 21, 2026, 12:20 a.m.
Created at: April 16, 2026, 12:40 p.m.