Triple

T21961581
Position Surface form Disambiguated ID Type / Status
Subject María E542342 entity
Predicate hasVariant P455 FINISHED
Object Marija 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: Marija | Statement: [María, hasVariant, Marija]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marija
Context triple: [María, hasVariant, Marija]
  • A. Marija chosen
    Marija is a feminine given name commonly used in Slavic and other European cultures, equivalent to "Maria" or "Mary."
  • B. Julijana
    Julijana is a feminine given name, commonly used in Slavic countries, that corresponds to the name Juliana in other languages.
  • C. Milica
    Milica is the Slavic given name of actress and model Milla Jovovich, reflecting her Eastern European heritage.
  • D. Emilija
    Emilija is a feminine given name commonly used in various Slavic and Baltic countries, equivalent to Emilia or Emily in English.
  • E. Majda
    Majda is a surname most notably associated with Andrew J. Majda, an influential American mathematician known for his work in applied mathematics and partial differential equations.
  • 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_69e0c47fab1081908dc74a6545dbb051 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f124572738819098cc669aafa53cc6 completed April 28, 2026, 9:19 p.m.
Created at: April 16, 2026, 8 p.m.