Triple

T5311057
Position Surface form Disambiguated ID Type / Status
Subject Mad Cows E119027 entity
Predicate director P255 FINISHED
Object Sara Sugarman
Sara Sugarman is a Welsh film director, actress, and screenwriter known for her work on independent comedies and dramas.
E509901 NE FINISHED

How this triple was built (4 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, director, Sara Sugarman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sara Sugarman
Context triple: [Mad Cows, director, Sara Sugarman]
  • A. 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.
  • B. Elaine Hyman
    Elaine Hyman is known primarily as the spouse of Lloyd Wright, the American architect and son of Frank Lloyd Wright.
  • C. Roberta Seidman
    Roberta Seidman was the wife of American actor John Garfield, a prominent film star of the 1930s and 1940s.
  • D. 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."
  • E. Sari Gilman
    Sari Gilman is a film editor best known for her work on the Academy Award–winning documentary "Taxi to the Dark Side."
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Sara Sugarman
Triple: [Mad Cows, director, Sara Sugarman]
Generated description
Sara Sugarman is a Welsh film director, actress, and screenwriter known for her work on independent comedies and dramas.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sara Sugarman
Target entity description: Sara Sugarman is a Welsh film director, actress, and screenwriter known for her work on independent comedies and dramas.
  • A. 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.
  • B. Elaine Hyman
    Elaine Hyman is known primarily as the spouse of Lloyd Wright, the American architect and son of Frank Lloyd Wright.
  • C. Roberta Seidman
    Roberta Seidman was the wife of American actor John Garfield, a prominent film star of the 1930s and 1940s.
  • D. 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."
  • E. Sari Gilman
    Sari Gilman is a film editor best known for her work on the Academy Award–winning documentary "Taxi to the Dark Side."
  • F. None of above. chosen

Provenance (5 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_69bf11033c448190ab64600913ee8a9c completed March 21, 2026, 9:43 p.m.
NEDg Description generation batch_69bf11c162f48190bdc56fea62575643 completed March 21, 2026, 9:46 p.m.
NED2 Entity disambiguation (via description) batch_69bf1237a644819081b1f1013e23cc66 completed March 21, 2026, 9:48 p.m.
Created at: March 20, 2026, 1:53 p.m.