Triple

T20709905
Position Surface form Disambiguated ID Type / Status
Subject Archaeopolis E509006 entity
Predicate locatedIn P40 FINISHED
Object Lazica 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: Lazica | Statement: [Archaeopolis, locatedIn, Lazica]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lazica
Context triple: [Archaeopolis, locatedIn, Lazica]
  • A. Lazica chosen
    Lazica was an ancient region on the eastern coast of the Black Sea, in what is now western Georgia, known historically as a Byzantine–Persian frontier kingdom.
  • B. Dardania
    Dardania was an ancient region in the central Balkans, roughly corresponding to parts of modern Kosovo and surrounding areas, known as a Roman and later Byzantine province.
  • C. Sarmato
    Sarmato is a small Italian municipality in the Emilia-Romagna region, known for its rural landscape and historic architecture.
  • D. Duklja
    Duklja was a medieval South Slavic principality in the western Balkans, roughly corresponding to parts of present-day Montenegro and northern Albania.
  • E. Moesia
    Moesia was an ancient Roman province located in the Balkans along the Danube River, encompassing parts of present-day Serbia and Bulgaria.
  • 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_69e0b4c40ad88190b81f77695366d328 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c1974ba08190b0e5ad529be95e4c completed April 21, 2026, 12:15 a.m.
Created at: April 16, 2026, 12:14 p.m.