Triple

T22071351
Position Surface form Disambiguated ID Type / Status
Subject Hugh Downs E545413 entity
Predicate familyName P18 FINISHED
Object Downs 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: Downs | Statement: [Hugh Downs, familyName, Downs]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Downs
Context triple: [Hugh Downs, familyName, Downs]
  • A. Downs chosen
    Downs is a surname of English origin borne by various notable individuals across fields such as entertainment, sports, and public life.
  • B. Downes
    Downes is an English surname borne by various notable individuals across fields such as music, sports, and public life.
  • C. Dowden
    Dowden is an English surname most notably associated in contemporary politics with British Conservative politician Oliver Dowden.
  • D. Overton
    Overton is a village in the Basingstoke and Deane district of Hampshire, England, known for its historic mill and rural character.
  • E. Overton
    Overton is a small unincorporated community in southeastern Nevada known as a gateway to the nearby Lake Mead National Recreation Area and the Valley of Fire State Park.
  • 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_69e11e344dfc81909b1d88a7221329c7 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f12888dcc08190b18d3d44d09ab943 completed April 28, 2026, 9:37 p.m.
Created at: April 16, 2026, 8:28 p.m.