Triple

T4506459
Position Surface form Disambiguated ID Type / Status
Subject Vertigo E101341 entity
Predicate keyFigure P256 FINISHED
Object Karen Berger E447159 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: Karen Berger | Statement: [Vertigo, keyFigure, Karen Berger]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karen Berger
Context triple: [Vertigo, keyFigure, Karen Berger]
  • A. Karen Berger chosen
    Karen Berger is an influential American comic book editor best known for founding and leading DC Comics' Vertigo imprint, which championed mature, creator-driven titles.
  • B. Barbara Guggenheim
    Barbara Guggenheim is a member of the prominent Guggenheim family, known for its significant influence in art patronage and philanthropy.
  • C. Patricia Fruen
    Patricia Fruen is an actress known for her role in the film "Way Down East."
  • D. Susan Anspach
    Susan Anspach was an American actress best known for her roles in influential 1970s films such as "Five Easy Pieces" and "Blume in Love," where she often portrayed complex, independent women.
  • E. Jean Doumanian
    Jean Doumanian is an American film and television producer known for her work on independent films, Broadway productions, and a tumultuous stint overseeing Saturday Night Live in the early 1980s.
  • 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_69bd43d175248190894dc58b5b395c26 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd56ff78748190bb667e70c69dc817 completed March 20, 2026, 2:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69bd7f760658819085ca8c631894b486 completed March 20, 2026, 5:10 p.m.
Created at: March 20, 2026, 1:01 p.m.