Triple

T16129058
Position Surface form Disambiguated ID Type / Status
Subject Maysie Hoy E391345 entity
Predicate notableWork P4 FINISHED
Object Good Deeds E1031655 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: Good Deeds | Statement: [Maysie Hoy, notableWork, Good Deeds]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Good Deeds
Context triple: [Maysie Hoy, notableWork, Good Deeds]
  • A. Good Deeds chosen
    Good Deeds is a 2012 romantic drama film written, directed by, and starring Tyler Perry, in which Brian J. White appears in a supporting role.
  • B. No Good Deed
    No Good Deed is a 2014 American thriller film starring Idris Elba and Taraji P. Henson, centered on a woman terrorized by an escaped convict who invades her home.
  • C. Good Works
    Good Works is an allegorical figure in the medieval morality play "Jedermann" (a German adaptation of "Everyman"), representing the personification of charitable deeds and moral actions.
  • D. Perfect Charity
    Perfect Charity is the official English title of the Second Vatican Council decree *Perfectae Caritatis* on the renewal and adaptation of religious life in the Catholic Church.
  • E. How to Be Good
    How to Be Good is a comic novel by British author Nick Hornby that explores morality, marriage, and midlife crisis through the perspective of a disillusioned doctor.
  • 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_69d87f1bb0988190b490d273dbf3fd03 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e20206a6f08190aa648d2bb11e7878 completed April 17, 2026, 9:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff2adf5848190a1dd58bc76dd4ffd completed May 10, 2026, 2:51 a.m.
Created at: April 10, 2026, 5:01 a.m.