Triple

T19071250
Position Surface form Disambiguated ID Type / Status
Subject Diwan Abatur E466795 entity
Predicate associatedDeity P1481 FINISHED
Object Abatur 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: Abatur | Statement: [Diwan Abatur, associatedDeity, Abatur]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Abatur
Context triple: [Diwan Abatur, associatedDeity, Abatur]
  • A. Abatur chosen
    Abatur is a central figure in Mandaean religion, often depicted as a divine judge who weighs the souls of the dead.
  • B. Atuda
    Atuda is an Israeli military-academic reserve program that allows selected recruits to complete higher education before serving in professional roles within the Israel Defense Forces.
  • C. Abur
    Abur is the traditional name for the Old Permic alphabet, an early writing system used for the Komi language in the medieval Perm region of Russia.
  • D. Atraxi
    The Atraxi are a crystalline, prison-ship–operating alien race from the Doctor Who universe who act as intergalactic jailers and judges.
  • E. Atsu
    Atsu is a Japanese given-name element commonly used as the first part of longer names such as Atsuko.
  • 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_69d8dd04f4488190b1121cc53ef2bfd6 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e19fa6948190bdf8e8ec022e12f2 completed April 20, 2026, 8:19 a.m.
Created at: April 10, 2026, 12:04 p.m.