Triple

T14355177
Position Surface form Disambiguated ID Type / Status
Subject Angela's Ashes E355953 entity
Predicate awarded P11 FINISHED
Object Boeke Prize E1096466 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: Boeke Prize | Statement: [Angela's Ashes, awarded, Boeke Prize]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Boeke Prize
Context triple: [Angela's Ashes, awarded, Boeke Prize]
  • A. Boeke Prize chosen
    The Boeke Prize is a South African literary award recognizing outstanding works of fiction, notably including Frank McCourt’s memoir "Angela’s Ashes."
  • B. Christophorus Prize
    The Christophorus Prize is an award recognizing notable contributions in the field of information technology and the development of the World Wide Web.
  • C. Multatuli Prize
    The Multatuli Prize is a Dutch literary award named after the writer Multatuli, given for outstanding works of literature in the Netherlands.
  • D. Fontane Prize
    The Fontane Prize is a German literary award named after writer Theodor Fontane, given in recognition of outstanding achievements in literature.
  • E. Yourcenar Prize
    The Yourcenar Prize is a French literary award named after writer Marguerite Yourcenar, honoring distinguished authors for the excellence of their body of work.
  • 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_69d82790a7e08190877e2d349b2e8d8e completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8f519bf881908615f4d47e0f77aa completed April 14, 2026, 7:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd550aef908190a7ec49e409f92dc7 completed May 8, 2026, 3:14 a.m.
Created at: April 10, 2026, 1:15 a.m.