Triple

T20001380
Position Surface form Disambiguated ID Type / Status
Subject Paul Ferroll E494336 entity
Predicate mainCharacter P1183 FINISHED
Object Paul Ferroll 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 Ferroll | Statement: [Paul Ferroll, mainCharacter, Paul Ferroll]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paul Ferroll
Context triple: [Paul Ferroll, mainCharacter, Paul Ferroll]
  • A. Paul Ferroll chosen
    Paul Ferroll is a mid-19th-century psychological crime novel by Caroline Clive, notable for its early and unconventional portrayal of a seemingly respectable man who has committed murder.
  • B. John Ferrar
    John Ferrar was a member of the prominent Ferrar family associated with the 17th-century Anglican religious community at Little Gidding and the brother and close collaborator of Nicholas Ferrar.
  • C. Edward McGowan
    Edward McGowan is the founder of St. George's University, a private international university best known for its medical school.
  • D. Paul Gilpin
    Paul Gilpin is a cinematographer best known for his work on the adventure film "Tarzan and the Lost City."
  • E. Paul Duguid
    Paul Duguid is a scholar of information studies and co-author of the influential book "The Social Life of Information" with John Seely Brown.
  • 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_69e661a222908190b88e1d11cb1b7ee3 completed April 20, 2026, 5:25 p.m.
Created at: April 11, 2026, 3:32 p.m.