Triple

T16097943
Position Surface form Disambiguated ID Type / Status
Subject Hot Bench E390533 entity
Predicate judge P3169 FINISHED
Object Tanya Acker E1197886 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: Tanya Acker | Statement: [Hot Bench, judge, Tanya Acker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tanya Acker
Context triple: [Hot Bench, judge, Tanya Acker]
  • A. Tanya Acker chosen
    Tanya Acker is an American civil litigator and television personality best known as a judge on the courtroom reality show "Hot Bench."
  • B. Kate Sacker
    Kate Sacker is a sharp, ambitious Assistant U.S. Attorney in the television drama "Billions," known for her legal acumen and political savvy.
  • C. Karen Akers
    Karen Akers is an American actress and cabaret singer known for her work on Broadway and in film, particularly in sophisticated musical and dramatic roles.
  • D. Tanya Vogel
    Tanya Vogel is a collegiate sports administrator best known for serving as the athletic director at George Washington University.
  • E. Jane Brucker
    Jane Brucker is an American actress best known for playing Lisa Houseman, the protagonist’s older sister, in the classic 1987 film "Dirty Dancing."
  • 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_69d87f198bc48190a8b7e53ca15b7ead completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e1ff6551a48190afb7e0c61e22b541 completed April 17, 2026, 9:37 a.m.
NED1 Entity disambiguation (via context triple) batch_69fffeed4e008190b1e8d924b9dc9d37 completed May 10, 2026, 3:43 a.m.
Created at: April 10, 2026, 4:59 a.m.