Triple

T22729927
Position Surface form Disambiguated ID Type / Status
Subject Lukas-Passion E562105 entity
Predicate hasCharacter P2308 FINISHED
Object Pilate NE NERFINISHED

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: Pilate | Statement: [Lukas-Passion, hasCharacter, Pilate]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pilate
Context triple: [Lukas-Passion, hasCharacter, Pilate]
  • A. Pilate
    Pilate is a commune in northern Haiti known for its rural character and location within the Nord department.
  • B. Pontius Pilate chosen
    Pontius Pilate was the Roman governor of Judea in the early 1st century CE, best known for presiding over the trial of Jesus and authorizing his crucifixion.
  • C. Caiaphas
    Caiaphas was the Jewish high priest who, according to the New Testament, played a central role in the trial and condemnation of Jesus before his crucifixion.
  • D. Coponius
    Coponius was a Roman prefect appointed by Emperor Augustus to govern Judea after the deposition of Herod Archelaus.
  • E. Pontius Telesinus
    Pontius Telesinus was a Samnite military leader and general who played a key role in the final resistance against Roman domination during the Social War and subsequent conflicts.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e24550859c81908727d91efc3a81b4 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f1792cb9cc8190a7c45032427bca1a completed April 29, 2026, 3:21 a.m.
Created at: April 17, 2026, 3:21 p.m.