Triple

T22722898
Position Surface form Disambiguated ID Type / Status
Subject exorcism of Asmodeus E561911 entity
Predicate hasCharacter P2308 FINISHED
Object Tobit 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: Tobit | Statement: [exorcism of Asmodeus, hasCharacter, Tobit]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tobit
Context triple: [exorcism of Asmodeus, hasCharacter, Tobit]
  • A. Tobit chosen
    Tobit is a deuterocanonical Jewish wisdom and adventure narrative, preserved in the Septuagint, that tells the story of a righteous Israelite and his son Tobias guided by the angel Raphael.
  • B. Tobias (Book of Tobit)
    Tobias is a central figure in the biblical Book of Tobit, known as the pious son of Tobit who undertakes a divinely guided journey with the angel Raphael.
  • C. Tobit Raphael
    Tobit Raphael is an actor best known for his role as Yo-Yo Santos in the comedy film "The Internship."
  • D. Tobia
    Tobia is a small town in Colombia known for its lush river valley setting and popular adventure sports like rafting and canyoning.
  • E. Giona
    Giona is an Italian given name, equivalent to Jonah, with biblical origins and shared etymological roots with the name Yonas.
  • 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_69e2454fc984819088213b58ee87a002 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f17926ae0c8190af8493cab6b15261 completed April 29, 2026, 3:21 a.m.
Created at: April 17, 2026, 3:20 p.m.