Triple

T21354465
Position Surface form Disambiguated ID Type / Status
Subject Stepan E526578 entity
Predicate variantOf P4680 FINISHED
Object Stephan 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: Stephan | Statement: [Stepan, variantOf, Stephan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stephan
Context triple: [Stepan, variantOf, Stephan]
  • A. Stephan chosen
    Stephan is a masculine given name, commonly used in German- and Dutch-speaking countries, that is a variant of the name Stephen.
  • B. Stephanas
    Stephanas is a biblical figure mentioned in the New Testament as one of the early Christian converts in Achaia and a supporter of the Apostle Paul.
  • C. Steffen
    Steffen is a surname most notably associated with Will Steffen, an influential climate scientist and researcher on Earth system dynamics and global environmental change.
  • D. Stephan Rick
    Stephan Rick is a German film director known for his work in thriller and crime dramas, including the feature film "The Super."
  • E. Stephan Zacharias
    Stephan Zacharias is a German film composer known for his dramatic and historically themed scores, including his work on the World War II film "Downfall."
  • 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_69e0b51cd5cc81909ac1187971e8a8ad completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e8af9aa9508190b756cc8e07084c8e completed April 22, 2026, 11:23 a.m.
Created at: April 16, 2026, 5:05 p.m.