Triple

T3879535
Position Surface form Disambiguated ID Type / Status
Subject Serbian Empire E92786 entity
Predicate capital P234 FINISHED
Object Prizren E231637 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: Prizren | Statement: [Serbian Empire, capital, Prizren]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Prizren
Context triple: [Serbian Empire, capital, Prizren]
  • A. Prizren chosen
    Prizren is a historic and culturally rich city in southern Kosovo, known for its well-preserved Ottoman-era architecture and diverse religious heritage.
  • B. Monastir
    Monastir, known today as Bitola in North Macedonia, is a historic Balkan city that played a significant strategic role during World War I.
  • C. Mitrovica
    Mitrovica is a divided city in northern Kosovo known for its ethnic tensions and strategic importance as a regional industrial and mining center.
  • D. Gjirokastër
    Gjirokastër is a historic stone-built city in southern Albania, recognized as a UNESCO World Heritage Site for its well-preserved Ottoman-era architecture.
  • E. Pristina
    Pristina is the capital and largest city of Kosovo, serving as its political, economic, and cultural center in the central Balkans.
  • 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_69aed9697de0819087c2559295ff3d12 completed March 9, 2026, 2:30 p.m.
NER Named-entity recognition batch_69aeec7438808190b6c90fcb3000ebe9 completed March 9, 2026, 3:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69b51c87214881908e03f5c770c58713 completed March 14, 2026, 8:29 a.m.
Created at: March 9, 2026, 3:20 p.m.