Triple

T22453564
Position Surface form Disambiguated ID Type / Status
Subject Maximus of Ephesus E555052 entity
Predicate contemporaryOf P6401 FINISHED
Object Julian the Apostate 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: Julian the Apostate | Statement: [Maximus of Ephesus, contemporaryOf, Julian the Apostate]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Julian the Apostate
Context triple: [Maximus of Ephesus, contemporaryOf, Julian the Apostate]
  • A. Julian the Apostate chosen
    Julian the Apostate was a 4th-century Roman emperor known for his attempt to restore paganism and roll back the spread of Christianity in the Roman Empire.
  • B. Julian of Eclanum
    Julian of Eclanum was a 5th-century Christian bishop and theologian best known as a leading defender of Pelagian views against Augustine’s doctrine of original sin.
  • C. Anicius Julianus
    Anicius Julianus was a member of the prominent late Roman Anicii family, known for its influential senatorial and political roles in the empire.
  • D. Julian
    Julian is a historic gold-mining town in San Diego County, California, known for its mountain scenery, apple orchards, and small-town charm.
  • E. Julian
    Julian is a masculine given name of Latin origin, commonly used in many English-speaking and European countries.
  • 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_69e11e5113208190ab58c6b595f9d1d0 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15b4d6368819082cafbbd83339fbf completed April 29, 2026, 1:13 a.m.
Created at: April 16, 2026, 8:48 p.m.