Triple

T19942908
Position Surface form Disambiguated ID Type / Status
Subject PostSecret E479350 entity
Predicate curatedBy P5107 FINISHED
Object Frank Warren 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: Frank Warren | Statement: [PostSecret, curatedBy, Frank Warren]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank Warren
Context triple: [PostSecret, curatedBy, Frank Warren]
  • A. Frank Warren
    Frank Warren is a prominent British boxing promoter and manager known for guiding the careers of numerous world champions and staging major boxing events in the UK.
  • B. Frank Warren chosen
    Frank Warren is an American author and entrepreneur best known for founding the community art project and blog PostSecret, which invites people to anonymously share their personal secrets on postcards.
  • C. Bob Arum
    Bob Arum is a prominent American boxing promoter and founder of Top Rank, known for promoting many of the sport’s biggest stars and events over several decades.
  • D. Lou Duva
    Lou Duva was a renowned American boxing trainer and manager known for guiding multiple world champions and being inducted into the International Boxing Hall of Fame.
  • E. Don Peterman
    Don Peterman was an American cinematographer known for his work on major Hollywood films across several decades, including comedies, dramas, and visual-effects-heavy productions.
  • 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_69d8e522a17c819095165d4d24939fd8 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65a63f2e48190ba1cb7a4f415e7f6 completed April 20, 2026, 4:55 p.m.
Created at: April 10, 2026, 1:54 p.m.