Triple

T15873873
Position Surface form Disambiguated ID Type / Status
Subject Kuzma E384896 entity
Predicate hasVariant P455 FINISHED
Object Cosmas E538539 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: Cosmas | Statement: [Kuzma, hasVariant, Cosmas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cosmas
Context triple: [Kuzma, hasVariant, Cosmas]
  • A. Cosmas chosen
    Cosmas is a Christian saint traditionally venerated as one of the twin physician-martyrs alongside his brother Damian.
  • B. Kosmas
    Kosmas is a traditional mountain village in the Parnon range of the southeastern Peloponnese in Greece, known for its scenic setting and historic stone architecture.
  • C. Agapius
    Agapius is traditionally regarded as one of the children of Saint Eustace in Christian hagiography.
  • D. Didymus
    Didymus is another name for the Apostle Thomas, one of Jesus Christ’s twelve original disciples in the New Testament.
  • E. Didymus
    Didymus is a Christian soldier and martyr featured in the legend of Saint Theodora of Alexandria, known for his courage and self-sacrifice.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d86da4e86481909f1325fdc971b5ec completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e155fc02688190b6f070882b846516 completed April 16, 2026, 9:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffa94e9b548190bec74e6d9790d241 completed May 9, 2026, 9:38 p.m.
Created at: April 10, 2026, 4:51 a.m.