Triple

T1033821
Position Surface form Disambiguated ID Type / Status
Subject Lorraine Gary E22312 entity
Predicate characterPortrayed P1507 FINISHED
Object Ellen Brody E78411 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: Ellen Brody | Statement: [Lorraine Gary, characterPortrayed, Ellen Brody]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ellen Brody
Context triple: [Lorraine Gary, characterPortrayed, Ellen Brody]
  • A. Ellen Brody chosen
    Ellen Brody is the resilient and protective wife of police chief Martin Brody in the Jaws film series, known for her role as a grounding family presence amid the shark-related terror.
  • B. Barbara Robbins
    Barbara Robbins is known as the wife of Jon Lindbergh, the son of famed aviator Charles Lindbergh.
  • C. Nancy Goodman
    Nancy Goodman is an American diplomat, businesswoman, and philanthropist best known for founding the Susan G. Komen Breast Cancer Foundation.
  • D. Audrey Bilger
    Audrey Bilger is an American academic and administrator who serves as the president of Reed College in Portland, Oregon.
  • E. Lynne Hollander
    Lynne Hollander is an American activist best known for her involvement in the 1960s Free Speech Movement at UC Berkeley and her longtime partnership with fellow activist Mario Savio.
  • 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_69a493d848848190aed4011b34b2e8d3 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b812c9948190a37c2b1d3d32ea38 completed March 1, 2026, 10:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69aef06424f48190bf3604cc342992b6 completed March 9, 2026, 4:08 p.m.
Created at: March 1, 2026, 7:41 p.m.