Triple

T16254132
Position Surface form Disambiguated ID Type / Status
Subject Kedesh E394585 entity
Predicate roleInBiblicalLaw P99376 FINISHED
Object asylum for unintentional killers 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: asylum for unintentional killers | Statement: [Kedesh, roleInBiblicalLaw, asylum for unintentional killers]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: roleInBiblicalLaw
Context triple: [Kedesh, roleInBiblicalLaw, asylum for unintentional killers]
  • A. roleInJudaism
    Indicates the specific religious, social, or institutional function an entity holds within the context of Judaism.
  • B. scripturalLawCode
    Indicates that one entity is a law code or set of legal prescriptions as defined or authorized by a particular scriptural or religious text for another entity.
  • C. roleInIslamicLaw
    Indicates the specific function, status, or authority an entity holds within the framework of Islamic legal principles and institutions.
  • D. religiousLawView
    Indicates a person's stance, interpretation, or opinion regarding a particular religious law or set of religious legal principles.
  • E. religiousLawAspect chosen
    Indicates that one entity represents a specific aspect, dimension, or component of a religious law associated with 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_69d87f2171208190951025e526947816 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e24598c9488190a92df7d8b1824724 completed April 17, 2026, 2:37 p.m.
PD Predicate disambiguation batch_69e219f259e88190bf49d8408c04178e completed April 17, 2026, 11:30 a.m.
Created at: April 10, 2026, 5:04 a.m.