Triple

T21836288
Position Surface form Disambiguated ID Type / Status
Subject Amy Redford E539127 entity
Predicate notableWork P4 FINISHED
Object Sunshine Cleaning 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: Sunshine Cleaning | Statement: [Amy Redford, notableWork, Sunshine Cleaning]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sunshine Cleaning
Context triple: [Amy Redford, notableWork, Sunshine Cleaning]
  • A. Sunshine Cleaning chosen
    Sunshine Cleaning is a 2008 indie dramedy film about two sisters who start a crime-scene cleanup business, starring Amy Adams and Emily Blunt.
  • B. Jefferson Cleaners
    Jefferson Cleaners is the dry-cleaning business owned and operated by George Jefferson in the television series "All in the Family" and its spin-off "The Jeffersons."
  • C. United CleanPlus
    United CleanPlus is United Airlines’ enhanced health and safety program focused on elevated cleaning, disinfection, and wellness standards throughout the travel experience.
  • D. Laundry Service
    "Laundry Service" is the breakthrough 2001 studio album by Colombian singer Shakira that marked her successful crossover into the English-language pop market.
  • E. Cleaners
    Cleaners is a crime thriller web series featuring Gina Gershon in a lead role as a professional assassin.
  • 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_69e0c475cda88190987d08f23caebdc1 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f0a7a7c368819094e0c4548be30798 completed April 28, 2026, 12:27 p.m.
Created at: April 16, 2026, 6:55 p.m.