Triple

T5311058
Position Surface form Disambiguated ID Type / Status
Subject Mad Cows E119027 entity
Predicate screenwriter P2831 FINISHED
Object Sara Sugarman E509901 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: Sara Sugarman | Statement: [Mad Cows, screenwriter, Sara Sugarman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sara Sugarman
Context triple: [Mad Cows, screenwriter, Sara Sugarman]
  • A. Sara Sugarman chosen
    Sara Sugarman is a Welsh film director, actress, and screenwriter known for her work on independent comedies and dramas.
  • B. Gail Berman
    Gail Berman is an American television and film producer and media executive known for her influential roles at major studios and for producing high-profile projects across network TV and Hollywood.
  • C. Elaine Hyman
    Elaine Hyman is known primarily as the spouse of Lloyd Wright, the American architect and son of Frank Lloyd Wright.
  • D. Roberta Seidman
    Roberta Seidman was the wife of American actor John Garfield, a prominent film star of the 1930s and 1940s.
  • E. Sandy Stern
    Sandy Stern is a film producer best known for his work on independent and cult-favorite movies, including the 1990 teen drama "Pump Up the Volume."
  • 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_69bd446b57bc8190a513d2e6c40314f3 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd85343ae08190bd9801ea4eac7003 completed March 20, 2026, 5:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf188988688190b4b08b5e0cda8cf5 completed March 21, 2026, 10:15 p.m.
Created at: March 20, 2026, 1:53 p.m.