Triple

T5699104
Position Surface form Disambiguated ID Type / Status
Subject Pliska E125613 entity
Predicate replacedByCapital P43447 FINISHED
Object Preslav E102446 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: Preslav | Statement: [Pliska, replacedByCapital, Preslav]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Preslav
Context triple: [Pliska, replacedByCapital, Preslav]
  • A. Preslav chosen
    Preslav is an ancient Bulgarian city that served as a major medieval political and cultural capital of the First Bulgarian Empire and a key center of Slavic literacy and Orthodox Christianity.
  • B. Ilija
    Ilija is a masculine given name of Slavic origin, commonly used in countries such as Bulgaria, Serbia, and North Macedonia.
  • C. Rastko
    Rastko, later known as Saint Sava, was a medieval Serbian prince who became a monk and is revered as the founder of the Serbian Orthodox Church and a key figure in Serbian medieval culture and education.
  • D. Vladislav
    Vladislav is a masculine given name of Slavic origin, commonly used in Russia and other Eastern European countries.
  • 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_69c0082c96988190b3a6a201edce472a completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0240ecef48190bdef10b38ecb2bd0 completed March 22, 2026, 5:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69c05a5c89b88190a397c6b1dcb9c3e8 completed March 22, 2026, 9:08 p.m.
Created at: March 22, 2026, 3:45 p.m.