Triple

T13616797
Position Surface form Disambiguated ID Type / Status
Subject As Good as It Gets E325336 entity
Predicate producer P490 FINISHED
Object Bridget Johnson
Bridget Johnson is a film producer best known for her work on the acclaimed romantic comedy-drama "As Good as It Gets."
E1140219 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: Bridget Johnson | Statement: [As Good as It Gets, producer, Bridget Johnson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bridget Johnson
Context triple: [As Good as It Gets, producer, Bridget Johnson]
  • A. Bridget Mason
    Bridget Mason is a woman known primarily as the daughter of Sir Joseph Mason.
  • B. Jennifer Johnson
    Jennifer Johnson is known as the mother of Quake, a character associated with this relationship.
  • C. Carrie Johnson
    Carrie Johnson is a British political activist and communications professional, best known as the wife of former UK Prime Minister Boris Johnson.
  • D. Bridget Dryden
    Bridget Dryden was the mother of the notable Puritan spiritual leader and religious dissenter Anne Hutchinson.
  • E. Bridget Sloan
    Bridget Sloan is an American artistic gymnast, Olympic silver medalist, and NCAA all-around champion who starred for the University of Florida Gators.
  • 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: Bridget Johnson
Triple: [As Good as It Gets, producer, Bridget Johnson]
Generated description
Bridget Johnson is a film producer best known for her work on the acclaimed romantic comedy-drama "As Good as It Gets."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Bridget Johnson
Target entity description: Bridget Johnson is a film producer best known for her work on the acclaimed romantic comedy-drama "As Good as It Gets."
  • A. Bridget Mason
    Bridget Mason is a woman known primarily as the daughter of Sir Joseph Mason.
  • B. Jennifer Johnson
    Jennifer Johnson is known as the mother of Quake, a character associated with this relationship.
  • C. Carrie Johnson
    Carrie Johnson is a British political activist and communications professional, best known as the wife of former UK Prime Minister Boris Johnson.
  • D. Bridget Dryden
    Bridget Dryden was the mother of the notable Puritan spiritual leader and religious dissenter Anne Hutchinson.
  • E. Bridget Sloan
    Bridget Sloan is an American artistic gymnast, Olympic silver medalist, and NCAA all-around champion who starred for the University of Florida Gators.
  • 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_69d8076aae28819092cf636190ee5529 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbb0ad0a7c81909c7972187202db96 completed April 12, 2026, 2:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69febfcbbf408190a87f471d2732148b completed May 9, 2026, 5:02 a.m.
NEDg Description generation batch_69fec21c8e1c8190b2a528acabdf2a49 completed May 9, 2026, 5:11 a.m.
NED2 Entity disambiguation (via description) batch_69fec2b612c8819084e4601dfff4ad81 completed May 9, 2026, 5:14 a.m.
Created at: April 9, 2026, 9:50 p.m.