Triple

T14159127
Position Surface form Disambiguated ID Type / Status
Subject Dorothy L. Sayers E350891 entity
Predicate familyName P18 FINISHED
Object Sayers E934336 NE FINISHED

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: Sayers | Statement: [Dorothy L. Sayers, familyName, Sayers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sayers
Context triple: [Dorothy L. Sayers, familyName, Sayers]
  • A. Sayers chosen
    Sayers is a surname most famously associated with Gale Sayers, the Hall of Fame American football running back for the Chicago Bears.
  • B. Dorothy L. Sayers
    Dorothy L. Sayers was a renowned British crime writer, best known for her Lord Peter Wimsey detective novels and her contributions to Christian apologetics and literary criticism.
  • C. Margery Hoffman Smith
    Margery Hoffman Smith was an American interior designer and arts advocate known for her influential work in Pacific Northwest modernism and her leadership in regional arts organizations.
  • D. Ellis Peters
    Ellis Peters was the pen name of English writer Edith Pargeter, best known for her historical mystery novels featuring Brother Cadfael.
  • E. Dilly Knox
    Dilly Knox was a British classics scholar and cryptanalyst renowned for his codebreaking work in both World Wars, particularly at Bletchley Park against German ciphers.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d8278775fc8190b0802d22ca2f495d completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de61377de48190a3470d28f0edd34a completed April 14, 2026, 3:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcf7ef4d80819098d210503f5d22e9 completed May 7, 2026, 8:37 p.m.
Created at: April 10, 2026, 12:58 a.m.