Triple

T18285204
Position Surface form Disambiguated ID Type / Status
Subject Ivan Vazov E437963 entity
Predicate familyName P18 FINISHED
Object Vazov 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: Vazov | Statement: [Ivan Vazov, familyName, Vazov]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vazov
Context triple: [Ivan Vazov, familyName, Vazov]
  • A. Vladimir Vazov
    Vladimir Vazov was a Bulgarian general renowned for his effective leadership during World War I, particularly in key battles on the Macedonian front.
  • B. Ivan Vazov chosen
    Ivan Vazov was a prominent Bulgarian writer and poet, often called the "Patriarch of Bulgarian literature," whose works played a crucial role in shaping modern Bulgarian national identity.
  • C. Pencho Slaveykov
    Pencho Slaveykov was a prominent Bulgarian poet, literary critic, and key figure of the Bulgarian modernist movement at the turn of the 20th century.
  • D. Petko Slaveykov
    Petko Slaveykov was a prominent 19th-century Bulgarian poet, publicist, and political figure who played a major role in the cultural and national awakening of Bulgaria.
  • E. Vasil Terziev
    Vasil Terziev is a Bulgarian entrepreneur and politician who serves as the mayor of Sofia.
  • 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_69d8b914530c8190b4474d862a2b2a1b completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e500f913d48190b41a1e37ca05e8b1 completed April 19, 2026, 4:21 p.m.
Created at: April 10, 2026, 10:35 a.m.