Triple

T11234641
Position Surface form Disambiguated ID Type / Status
Subject Demas E265910 entity
Predicate roleIn2Timothy P27433 FINISHED
Object example of one who deserted Paul LITERAL 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: example of one who deserted Paul | Statement: [Demas, roleIn2Timothy, example of one who deserted Paul]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: roleIn2Timothy
Context triple: [Demas, roleIn2Timothy, example of one who deserted Paul]
  • A. ecclesiasticalRole
    Indicates that one entity holds or is assigned a specific religious or church-related office, function, or position in relation to another entity.
  • B. biblicalFigureRole chosen
    Indicates the specific role, function, or office that a biblical figure holds within a biblical narrative or tradition.
  • C. liturgicalRole
    Indicates the specific function or position an entity holds within a religious or liturgical context.
  • D. theologicalRole
    Indicates a relationship where an entity holds or is assigned a specific function, office, or status within a theological or religious framework.
  • E. ecclesialRole
    Indicates that one entity holds or is assigned a specific role, office, or function within a church or ecclesiastical structure in relation to another entity.
  • F. None of above.

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_69d6aac656d48190b275efaa7d6074ee completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7e903b8ec81909f9c89776d35c650 completed April 9, 2026, 5:59 p.m.
PD Predicate disambiguation batch_69d75cfdf7a88190aae21572e57ef208 completed April 9, 2026, 8:02 a.m.
Created at: April 8, 2026, 9:30 p.m.