Triple

T9601892
Position Surface form Disambiguated ID Type / Status
Subject Preki E231869 entity
Predicate givenName P17 FINISHED
Object Predrag E394139 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: Predrag | Statement: [Preki, givenName, Predrag]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Predrag
Context triple: [Preki, givenName, Predrag]
  • A. Predrag chosen
    Predrag is the given first name of former Serbian professional basketball player Peja Stojaković.
  • B. Predrag Radosavljević
    Predrag Radosavljević, better known as Preki, is a retired Serbian-American attacking midfielder and coach who starred in Major League Soccer and represented the United States national team.
  • C. Pavle
    Pavle is a South Slavic male given name commonly used in countries such as Serbia, Croatia, and Montenegro, equivalent to Paul in English.
  • D. Predrag Danilović
    Predrag Danilović is a former Serbian professional basketball star, widely regarded as one of Europe’s top shooting guards of the 1990s and a key figure for both club and national teams.
  • E. Petar
    Petar is a given name commonly used in Slavic countries, equivalent to the English name Peter.
  • 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_69ca8484838c8190b2049199d22fef70 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9a3a49608190ad1f65195e4d5cda completed April 1, 2026, 10:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69d19f641c3081908084a3574e20457f completed April 4, 2026, 11:31 p.m.
Created at: March 30, 2026, 8:07 p.m.