Triple

T19637459
Position Surface form Disambiguated ID Type / Status
Subject Vuk Branković E471436 entity
Predicate spouse P13 FINISHED
Object Mara Lazarević 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: Mara Lazarević | Statement: [Vuk Branković, spouse, Mara Lazarević]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mara Lazarević
Context triple: [Vuk Branković, spouse, Mara Lazarević]
  • A. Mara Lazarević chosen
    Mara Lazarević was a medieval Serbian noblewoman, known as a daughter of Prince Lazar of Serbia and a member of the influential Lazarević dynasty.
  • B. Jelena Lazarević
    Jelena Lazarević is a member of the Lazarević family, recognized in connection with Teodora Lazarević.
  • C. Jelena Jovanović
    Jelena Jovanović was the wife of Karađorđe Petrović, the leader of the First Serbian Uprising and founder of the Karađorđević dynasty.
  • D. Dragana Lazarević
    Dragana Lazarević is a Serbian individual known primarily as the sister of Vuk Lazarević, a historical figure from the medieval Lazarević noble family.
  • E. Milana Savić
    Milana Savić is the mother of Serbian professional footballer Sergej Milinković-Savić.
  • 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_69d8e511f28481909f4bc3ea9191e54a completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e64107f3fc8190ace6ae67287d280c completed April 20, 2026, 3:06 p.m.
Created at: April 10, 2026, 1:44 p.m.