Triple

T16374566
Position Surface form Disambiguated ID Type / Status
Subject Flora Purim E397647 entity
Predicate performedWith P9966 FINISHED
Object George Duke E735689 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: George Duke | Statement: [Flora Purim, performedWith, George Duke]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George Duke
Context triple: [Flora Purim, performedWith, George Duke]
  • A. George Duke chosen
    George Duke was an influential American keyboardist, composer, and producer known for his work in jazz fusion, funk, and R&B, as well as collaborations with numerous prominent artists.
  • B. Robert Dukes
    Robert Dukes is an author best known for writing the second installment of the "Bound" series.
  • C. Gerald de Windsor
    Gerald de Windsor was an Anglo-Norman nobleman and royal official in Wales whose descendants, the Geraldines, became a powerful dynastic family in Ireland and Britain.
  • D. Edward King
    Edward King is a writer best known for authoring the work associated with the title "All Summer Long."
  • E. Godfrey Cambridge
    Godfrey Cambridge was an American comedian and actor known for his sharp social satire and prominent roles in 1960s and 1970s film and television.
  • 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_69d87f2880b48190ae1a9673a3bbef80 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e319d6942081909616a2c6efee9967 completed April 18, 2026, 5:42 a.m.
NED1 Entity disambiguation (via context triple) batch_6a003561f83481909223c99bb83ebdf4 completed May 10, 2026, 7:36 a.m.
Created at: April 10, 2026, 5:08 a.m.