Triple

T22141333
Position Surface form Disambiguated ID Type / Status
Subject Boris-Mihail E547164 entity
Predicate laterCapitalInfluence P23136 FINISHED
Object Preslav 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: Preslav | Statement: [Boris-Mihail, laterCapitalInfluence, Preslav]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Preslav
Context triple: [Boris-Mihail, laterCapitalInfluence, 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. Svetoslav
    Svetoslav is a Slavic given name, historically borne by various Eastern European rulers, nobles, and cultural figures.
  • C. Borislav
    Borislav is a masculine given name of Slavic origin, commonly used in Eastern European countries.
  • D. Ilija
    Ilija is a masculine given name of Slavic origin, commonly used in countries such as Bulgaria, Serbia, and North Macedonia.
  • E. Vaslav
    Vaslav is the given name of Vaslav Nijinsky, the legendary early 20th-century ballet dancer and choreographer renowned for his groundbreaking work with the Ballets Russes.
  • 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_69e11e3a95d88190a3bd80d9471976c3 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f129beb6c8819083be3b7479bc032f completed April 28, 2026, 9:42 p.m.
Created at: April 16, 2026, 8:32 p.m.