Triple

T19470708
Position Surface form Disambiguated ID Type / Status
Subject Young Mungo E487114 entity
Predicate author P4 FINISHED
Object Douglas Stuart 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: Douglas Stuart | Statement: [Young Mungo, author, Douglas Stuart]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Douglas Stuart
Context triple: [Young Mungo, author, Douglas Stuart]
  • A. Douglas Stuart chosen
    Douglas Stuart is a Scottish-American novelist best known for his debut novel "Shuggie Bain," which won the Booker Prize.
  • B. Marlon James
    Marlon James is a Jamaican novelist and Booker Prize winner known for his ambitious, genre-blending works that explore history, violence, and Black identity.
  • C. Eleanor Catton
    Eleanor Catton is a New Zealand novelist best known for her Booker Prize–winning historical novel "The Luminaries."
  • D. Dermot Povey
    Dermot Povey is a fictional character from the British sitcom "Men Behaving Badly," known as one of the show's central male leads.
  • E. Martin Sixsmith
    Martin Sixsmith is a British journalist, author, and former BBC correspondent known for his investigative writing, including the book that inspired the film "Philomena."
  • 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_69d8e8d86d608190bd199a98d0297f27 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e633e809008190b0021d41b99f9700 completed April 20, 2026, 2:10 p.m.
Created at: April 10, 2026, 1:39 p.m.