Triple

T19489468
Position Surface form Disambiguated ID Type / Status
Subject Miloš Obilić E487608 entity
Predicate hasAlternativeName P39 FINISHED
Object Miloš Kobilić 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: Miloš Kobilić | Statement: [Miloš Obilić, hasAlternativeName, Miloš Kobilić]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Miloš Kobilić
Context triple: [Miloš Obilić, hasAlternativeName, Miloš Kobilić]
  • A. Miloš Kobilić chosen
    Miloš Kobilić is an alternative name for Miloš Obilić, the legendary Serbian knight celebrated in epic poetry for assassinating Ottoman Sultan Murad I at the Battle of Kosovo.
  • B. Dragan Kićanović
    Dragan Kićanović is a former Yugoslav basketball star widely regarded as one of Europe’s greatest shooting guards of the 1970s and early 1980s.
  • C. Jakov Milatović
    Jakov Milatović is a Montenegrin economist and politician who became a prominent reformist leader and head of state in the early 2020s.
  • D. Momčilo Đujić
    Momčilo Đujić was a Serbian Orthodox priest and Chetnik commander who led nationalist and collaborationist forces in the Balkans during World War II.
  • E. Borivoj Dovniković
    Borivoj Dovniković was a prominent Croatian animator, cartoonist, and film director known for his influential work in Zagreb’s school of animated film.
  • 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_69d8e8d924388190b847cb15bb3d0aff completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6348ad4088190b530f47efca90165 completed April 20, 2026, 2:13 p.m.
Created at: April 10, 2026, 1:39 p.m.