Triple

T17957321
Position Surface form Disambiguated ID Type / Status
Subject Saint Cornelius E448985 entity
Predicate title P38 FINISHED
Object Saint Cornelius 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: Saint Cornelius | Statement: [Saint Cornelius, title, Saint Cornelius]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saint Cornelius
Context triple: [Saint Cornelius, title, Saint Cornelius]
  • A. Saint Cornelius chosen
    Saint Cornelius was a 3rd-century pope and Christian martyr venerated as a saint in the Catholic Church for his leadership during the persecution of Christians under the Roman Empire.
  • B. Saint Marcellinus
    Saint Marcellinus was an early Christian martyr and pope venerated for his steadfast faith during the Roman persecutions.
  • C. Saint Cataldus
    Saint Cataldus was a 7th-century Irish monk and bishop venerated as a Christian saint, particularly associated with Taranto in southern Italy.
  • D. Saint Geminianus
    Saint Geminianus is a Christian saint venerated as a protector and patron, particularly associated with the Italian town of San Gimignano that bears his name.
  • E. Saint Emygdius
    Saint Emygdius is a Christian martyr and bishop venerated especially in central Italy, widely regarded as a protector against earthquakes.
  • 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_69d8b9f8cca8819099836916c56b7c95 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4afb0afe08190964e771ec632fa1e completed April 19, 2026, 10:34 a.m.
Created at: April 10, 2026, 10:21 a.m.