Triple

T12141784
Position Surface form Disambiguated ID Type / Status
Subject Susan Harris E289200 entity
Predicate created P538 FINISHED
Object Good & Evil E965083 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 & Evil | Statement: [Susan Harris, created, Good & Evil]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Good & Evil
Context triple: [Susan Harris, created, Good & Evil]
  • A. Good & Evil chosen
    Good & Evil is a short-lived 1991 American sitcom created by Susan Harris that satirized soap operas and family rivalries.
  • B. Good and Evil
    Good and Evil is a philosophical work by Martin Buber that explores the nature of morality, human freedom, and the ethical dimensions of good and evil in human relationships.
  • C. Good and Evil
    "Good and Evil" is a song by Japanese singer Rei Momo.
  • D. The School for Good and Evil
    The School for Good and Evil is a fantasy film adaptation of Soman Chainani’s novel, following two best friends sent to a magical school that trains heroes and villains.
  • E. Nimona
    Nimona is an animated science-fantasy film, based on ND Stevenson’s graphic novel, that follows a shapeshifting teenager who teams up with a framed knight in a futuristic medieval world.
  • 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_69d6ab4c6710819097a9d228382dde43 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d915a9838081909622cc14df2a2582 completed April 10, 2026, 3:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69f60a7baee88190a32a5a3cd0b8a326 completed May 2, 2026, 2:30 p.m.
Created at: April 8, 2026, 9:49 p.m.