Triple

T21250776
Position Surface form Disambiguated ID Type / Status
Subject Ted Kramer E523737 entity
Predicate createdBy P806 FINISHED
Object Avery Corman 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: Avery Corman | Statement: [Ted Kramer, createdBy, Avery Corman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Avery Corman
Context triple: [Ted Kramer, createdBy, Avery Corman]
  • A. Avery Corman chosen
    Avery Corman is an American novelist best known for writing the book "Kramer vs. Kramer," which was adapted into an Academy Award–winning film.
  • B. Ben Demaree
    Ben Demaree is a cinematographer and filmmaker known for his work on low-budget genre films, including fantasy and science fiction titles.
  • C. John Landgraf
    John Landgraf is an American television executive best known as the longtime head of FX Networks and FX Productions, where he has overseen numerous critically acclaimed series.
  • D. Charlie Ebersol
    Charlie Ebersol is an American television and film producer and entrepreneur best known for co-founding the short-lived professional football league, the Alliance of American Football.
  • E. Alex Groesbeck
    Alex Groesbeck was a Republican politician who served as the 30th governor of Michigan in the early 20th century.
  • 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_69e0b5146c108190adc9adb73e90abff completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7359da6e08190a96c471463c2388d completed April 21, 2026, 8:30 a.m.
Created at: April 16, 2026, 3:56 p.m.