Triple

T19547436
Position Surface form Disambiguated ID Type / Status
Subject The Killing (1956 film) E489110 entity
Predicate editor P1954 FINISHED
Object Betty Steinberg 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: Betty Steinberg | Statement: [The Killing (1956 film), editor, Betty Steinberg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Betty Steinberg
Context triple: [The Killing (1956 film), editor, Betty Steinberg]
  • A. Betty Steinberg chosen
    Betty Steinberg is a film editor best known for her work on the crime drama film "The Killing."
  • B. Pam Katz
    Pam Katz is an American screenwriter known for co-writing historical and biographical films, including the 2012 drama "Hannah Arendt."
  • C. Betty Cohen
    Betty Cohen is an American television executive best known as the founding president of Cartoon Network and a pioneering figure in cable children’s programming.
  • D. Edie Landau
    Edie Landau was an American film and television producer known for her work on acclaimed projects such as "Long Day's Journey Into Night" and for co-founding the production company Ely Landau, Inc.
  • E. Rhoda Makoff
    Rhoda Makoff is an educator best known for founding Crossroads School, an independent progressive school in Santa Monica, California.
  • 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_69d8e8db5b6c8190984b61f91981f575 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63d2d8a6081908e9bb3a6f5d85896 completed April 20, 2026, 2:50 p.m.
Created at: April 10, 2026, 1:41 p.m.