Triple

T22667432
Position Surface form Disambiguated ID Type / Status
Subject The Tragical History of Doctor Faustus E559827 entity
Predicate mainCharacter P1183 FINISHED
Object Good Angel 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: Good Angel | Statement: [The Tragical History of Doctor Faustus, mainCharacter, Good Angel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Good Angel
Context triple: [The Tragical History of Doctor Faustus, mainCharacter, Good Angel]
  • A. Good Angel chosen
    Good Angel is a moralizing, conscience-like figure in the Faust legend who urges Doctor Faustus to repent and choose salvation over damnation.
  • B. Dobrý anjel
    Dobrý anjel is a Slovak charitable organization that provides financial assistance to families with children suffering from serious illnesses.
  • C. El Ángel
    El Ángel is a famous victory column and iconic symbol of Mexico City commemorating the country’s independence.
  • D. El Ángel
    El Ángel is an Argentine crime drama film that portrays the life of a charming yet remorseless young serial killer in 1970s Buenos Aires.
  • E. The Guardian Angel
    The Guardian Angel is a short story by Hans Christian Andersen that tells of a protective celestial being guiding a child’s soul to heaven.
  • 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_69e2454a158c819093b8e35f5045efb6 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1781ceca08190ba1309570e81c5af completed April 29, 2026, 3:16 a.m.
Created at: April 17, 2026, 3:09 p.m.