Triple

T21511101
Position Surface form Disambiguated ID Type / Status
Subject Horace Giddens E530720 entity
Predicate conflictsWith P4897 FINISHED
Object Regina Giddens 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: Regina Giddens | Statement: [Horace Giddens, conflictsWith, Regina Giddens]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Regina Giddens
Context triple: [Horace Giddens, conflictsWith, Regina Giddens]
  • A. Regina Giddens chosen
    Regina Giddens is the ruthless, ambitious Southern matriarch at the center of Lillian Hellman’s play "The Little Foxes," known for her manipulative pursuit of wealth and power.
  • B. Mary Elfrieda Scruggs
    Mary Elfrieda Scruggs, better known as Mary Lou Williams, was an influential American jazz pianist, composer, and arranger whose career spanned swing, bebop, and beyond.
  • C. Louise Scruggs
    Louise Scruggs was a pioneering music manager and businesswoman in bluegrass and country music, best known for managing the career of Earl Scruggs and the duo Flatt & Scruggs.
  • D. Maureen McGuire
    Maureen McGuire is best known as the former wife of American singer-songwriter Michael Bolton.
  • E. Betsy Brantley
    Betsy Brantley is an American actress known for her work in film, television, and theater, including roles in productions such as "The Princess Bride" and "Deep Impact."
  • 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_69e0c45c81f08190a6b8bbb70a45aae7 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e9ea863b18819080e3ff249b10ec28 completed April 23, 2026, 9:46 a.m.
Created at: April 16, 2026, 6:25 p.m.