Triple

T20386267
Position Surface form Disambiguated ID Type / Status
Subject The Good Mother E497963 entity
Predicate producer P490 FINISHED
Object Arlene Donovan 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: Arlene Donovan | Statement: [The Good Mother, producer, Arlene Donovan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arlene Donovan
Context triple: [The Good Mother, producer, Arlene Donovan]
  • A. Arlene Donovan chosen
    Arlene Donovan is a film producer best known for her work on the acclaimed 1984 drama "Places in the Heart."
  • B. Yvonne Donovan
    Yvonne Donovan is a fictional character who appears in the science fiction novel "Donovan's Brain."
  • C. Carmen Greer
    Carmen Greer is a central character in Lee Child’s Jack Reacher novel "Echo Burning," portrayed as a troubled Texas woman who enlists Reacher’s help amid an abusive marriage and a web of family secrets.
  • D. Brenda Kerrigan
    Brenda Kerrigan is best known as the mother of American figure skater and Olympic medalist Nancy Kerrigan.
  • E. Lisa Masterson
    Lisa Masterson is an American obstetrician-gynecologist and television personality best known for co-hosting the medical talk show "The Doctors."
  • 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_69e0b4a71ebc8190b153a36c738730f4 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6790bcef481909453d19c846ab420 completed April 20, 2026, 7:05 p.m.
Created at: April 16, 2026, 11:28 a.m.