Triple

T37146511
Position Surface form Disambiguated ID Type / Status
Subject Siege of Barcelona (801) E920254 entity
Predicate hasReligionOfAttackers P26483 FINISHED
Object Christianity E348 NE 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: Christianity | Statement: [Siege of Barcelona (801), hasReligionOfAttackers, Christianity]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasReligionOfAttackers
Context triple: [Siege of Barcelona (801), hasReligionOfAttackers, Christianity]
  • A. religionOfPerpetrators chosen
    Indicates the religious affiliation or belief system associated with the individuals who carried out a particular act or offense.
  • B. hasReligionOfBelligerents
    Indicates that the belligerent parties in a conflict are associated with a particular religion or religious affiliation.
  • C. religionOfDefenders
    Indicates the religious affiliation practiced or associated with the defenders in a given context.
  • D. hasReligious
    Indicates that an entity is associated with, practices, or adheres to a particular religion or religious affiliation.
  • E. hasDefendantReligion
    Indicates that a specified religion is the religious affiliation of the defendant in a legal case.
  • F. None of above.

Provenance (4 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_69f76e9f87c08190b4c8f7fafbd8345a completed May 3, 2026, 3:49 p.m.
NER Named-entity recognition batch_6a037c8e2c648190a65fc9c7872861af completed May 12, 2026, 7:16 p.m.
NED1 Entity disambiguation (via context triple) batch_6a3f6a2773ac8190928c55ab86886f55 completed June 27, 2026, 6:13 a.m.
PD Predicate disambiguation batch_6a037a11efc08190bb7cacc1325b4dc6 completed May 12, 2026, 7:05 p.m.
Created at: May 3, 2026, 4:15 p.m.