Triple

T21911750
Position Surface form Disambiguated ID Type / Status
Subject Belk family E541081 entity
Predicate hasNotableMember P304 FINISHED
Object William Henry Belk 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: William Henry Belk | Statement: [Belk family, hasNotableMember, William Henry Belk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: William Henry Belk
Context triple: [Belk family, hasNotableMember, William Henry Belk]
  • A. William Henry Belk chosen
    William Henry Belk was an American businessman and philanthropist best known for founding the Belk department store chain in the late 19th century.
  • B. Charles B. Mulvehill
    Charles B. Mulvehill was a film producer best known for his work on the cult classic dark comedy "Harold and Maude."
  • C. Roy E. Crummer
    Roy E. Crummer was a prominent businessman and philanthropist whose contributions led to the naming of the Crummer Graduate School of Business at Rollins College in his honor.
  • D. Edmund B. Sebree
    Edmund B. Sebree was a United States Army major general who distinguished himself as a combat commander in the European Theater during World War II.
  • E. Oscar E. Teagarden
    Oscar E. Teagarden was a judge who served on the United States Court of Customs and Patent Appeals, contributing to the development of U.S. customs and patent law.
  • 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_69e0c47c4b9c8190a5586a75f5f36453 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f121da36e88190b42b82641ec54a19 completed April 28, 2026, 9:08 p.m.
Created at: April 16, 2026, 7:41 p.m.