Triple

T17803810
Position Surface form Disambiguated ID Type / Status
Subject Battle of Cerami E444500 entity
Predicate religiousAffiliationOpponents P45 FINISHED
Object Sunni Muslim 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: Sunni Muslim | Statement: [Battle of Cerami, religiousAffiliationOpponents, Sunni Muslim]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: religiousAffiliationOpponents
Context triple: [Battle of Cerami, religiousAffiliationOpponents, Sunni Muslim]
  • A. primaryOpponentsReligion
    Indicates the religion or belief system followed by an entity’s main or primary opponent.
  • B. religiousAffiliation chosen
    Indicates that one entity has a specified religious association, belief system, or denominational membership.
  • C. religiousSide
    Indicates that one entity is aligned with, belongs to, or represents a particular religious faction, denomination, or side in a religious context.
  • D. religiousConstituency
    Indicates that one entity serves as a religious constituency or faith-based voter base for another entity, typically in a political or organizational context.
  • E. otherRivalReligion
    Indicates that one entity follows or is associated with a religion that is a rival or competing faith to the religion 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_69d8b9efe370819095cd219b143ae727 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e48802bcfc8190a138164d11081ab8 completed April 19, 2026, 7:45 a.m.
PD Predicate disambiguation batch_69e3d8de28688190844b65acf6af54e6 completed April 18, 2026, 7:17 p.m.
Created at: April 10, 2026, 10:14 a.m.