Triple

T20011337
Position Surface form Disambiguated ID Type / Status
Subject Ogdred Weary E494595 entity
Predicate basedOn P98 FINISHED
Object Edward Gorey (name anagram) 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: Edward Gorey (name anagram) | Statement: [Ogdred Weary, basedOn, Edward Gorey (name anagram)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Edward Gorey (name anagram)
Context triple: [Ogdred Weary, basedOn, Edward Gorey (name anagram)]
  • A. Edward Gorey chosen
    Edward Gorey was an American writer and illustrator known for his macabre, darkly humorous pen-and-ink drawings and gothic-tinged picture books.
  • B. Edward Grigg
    Edward Grigg was a British colonial administrator, politician, and writer who served as Governor of Kenya and was active in early 20th-century imperial and political circles.
  • C. Charles Giblyn
    Charles Giblyn was an early 20th-century American film director and actor active during the silent film era.
  • D. Charles Dexter
    Charles Dexter is a personal name shared by multiple individuals, most notably associated with fictional or historical figures bearing the surname Dexter.
  • E. Harry Bloom
    Harry Bloom was a South African-born lawyer, journalist, and anti-apartheid activist who later became a writer and academic in Australia.
  • 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_69da626b2d748190886981ea90c8b2ea completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e662362df48190abf16129eea39985 completed April 20, 2026, 5:28 p.m.
Created at: April 11, 2026, 3:33 p.m.