Triple

T16492249
Position Surface form Disambiguated ID Type / Status
Subject Boris Trajkovski E400594 entity
Predicate spouse P13 FINISHED
Object Vilma Trajkovska E1219238 NE FINISHED

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: Vilma Trajkovska | Statement: [Boris Trajkovski, spouse, Vilma Trajkovska]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vilma Trajkovska
Context triple: [Boris Trajkovski, spouse, Vilma Trajkovska]
  • A. Tereza Srbova
    Tereza Srbova is a Czech-born actress and model known for her roles in international films and television, often portraying enigmatic or sophisticated characters.
  • B. Violeta Gligorova chosen
    Violeta Gligorova was the wife of Kiro Gligorov, the first President of independent Macedonia.
  • C. Stanislava Brezovar
    Stanislava Brezovar was a Slovenian ballerina best known for her distinguished career at the Ljubljana Opera Ballet and her long partnership with conductor Carlos Kleiber.
  • D. Nena Danevic
    Nena Danevic is a film editor best known for her Academy Award–winning work on the 1984 historical drama "Amadeus."
  • E. Katerina Goseva-Popstojanova
    Katerina Goseva-Popstojanova is a computer scientist known for her research in software reliability, security, and quantitative evaluation of complex software systems.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d883813098819084f5409539723b59 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e32e30cb648190a52cb32896c4ac5a completed April 18, 2026, 7:09 a.m.
NED1 Entity disambiguation (via context triple) batch_6a006ed4a7008190ab1ad5cbf80dc119 completed May 10, 2026, 11:41 a.m.
Created at: April 10, 2026, 5:13 a.m.