Triple

T14201850
Position Surface form Disambiguated ID Type / Status
Subject Anti-sacrilege law E351982 entity
Predicate offenseDefined P26615 FINISHED
Object profanation of the consecrated host 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: profanation of the consecrated host | Statement: [Anti-sacrilege law, offenseDefined, profanation of the consecrated host]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: offenseDefined
Context triple: [Anti-sacrilege law, offenseDefined, profanation of the consecrated host]
  • A. offense
    Indicates that one entity commits, causes, or is responsible for a violation, wrongdoing, or rule-breaking act against another entity or governing norms.
  • B. definesOffence chosen
    Indicates that one entity specifies or establishes the nature, elements, or scope of an offence associated with another entity.
  • C. offenseNicknamed
    Indicates that an offensive unit, team, or strategy is commonly referred to by a particular nickname.
  • D. offensiveCharacteristic
    Indicates that one entity possesses a trait, behavior, or quality that is considered insulting, disrespectful, or likely to cause offense to another entity or group.
  • E. offenceCognizable
    Indicates that the offence is of a type for which police may initiate investigation and arrest without requiring prior permission or a warrant from a magistrate.
  • 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_69d827894ac0819097803e57f3227b23 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de61f589a08190b71ad4e69d92ffd0 completed April 14, 2026, 3:49 p.m.
PD Predicate disambiguation batch_69de05bcd7d48190a4848d9320404aa6 completed April 14, 2026, 9:15 a.m.
Created at: April 10, 2026, 1:05 a.m.