Triple

T18649530
Position Surface form Disambiguated ID Type / Status
Subject Old Academy E455892 entity
Predicate hasNotableMember P304 FINISHED
Object Philip of Opus 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: Philip of Opus | Statement: [Old Academy, hasNotableMember, Philip of Opus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Philip of Opus
Context triple: [Old Academy, hasNotableMember, Philip of Opus]
  • A. Philip of Opus chosen
    Philip of Opus was an ancient Greek philosopher and member of Plato’s circle, traditionally credited with editing and possibly completing Plato’s dialogue "Laws."
  • B. Ildephonsus
    Ildephonsus is a 7th-century Archbishop of Toledo venerated as a Catholic saint, renowned for his theological writings and strong devotion to the Virgin Mary.
  • C. Agapius
    Agapius is traditionally regarded as one of the children of Saint Eustace in Christian hagiography.
  • D. Phrasius
    Phrasius is a minor figure in Greek mythology known primarily as one of the sons of Neleus, the king of Pylos.
  • E. Filostrato
    Filostrato is a narrative poem by Giovanni Boccaccio that retells the tragic love story of Troilus and Criseyde, serving as a key source for later adaptations such as Chaucer’s version.
  • 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_69d8d38ea1e88190997e9b231190ba6f completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5500fd7cc819095c5e742013b8d75 completed April 19, 2026, 9:58 p.m.
Created at: April 10, 2026, 11:47 a.m.