Triple

T11856316
Position Surface form Disambiguated ID Type / Status
Subject Pannonia Savia E282047 entity
Predicate majorCity P316 FINISHED
Object Emona E261601 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: Emona | Statement: [Pannonia Savia, majorCity, Emona]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Emona
Context triple: [Pannonia Savia, majorCity, Emona]
  • A. Emona chosen
    Emona was an ancient Roman city located on the site of present-day Ljubljana, serving as a key urban and military center in the province of Pannonia.
  • B. Emona
    Emona is a small coastal settlement on Bulgaria’s Black Sea coast, situated close to Cape Emine.
  • C. Salona
    Salona was an important ancient Roman city on the Adriatic coast, serving as the chief urban center of the province of Dalmatia in present-day Croatia.
  • D. Salona
    Salona is a historic town in central Greece that served as an important medieval stronghold under various foreign rulers, including Catalan lords.
  • E. Bled
    Bled is a picturesque Slovenian town in the Julian Alps, famed for its glacial lake with an island church and a medieval clifftop castle.
  • 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_69d6ab287ba48190a5178779fd19b9b7 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8a699089c8190b7a298baf13dcded completed April 10, 2026, 7:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69f167d9b9e8819093582637941fc5ca completed April 29, 2026, 2:07 a.m.
Created at: April 8, 2026, 9:43 p.m.