Triple

T8377651
Position Surface form Disambiguated ID Type / Status
Subject Julius Nepos E197614 entity
Predicate placeOfDeath P21 FINISHED
Object Salona E90382 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: Salona | Statement: [Julius Nepos, placeOfDeath, Salona]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Salona
Context triple: [Julius Nepos, placeOfDeath, Salona]
  • A. Salona chosen
    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.
  • B. Aquileia
    Aquileia was an important ancient Roman city and trading hub in northeastern Italy, near the Adriatic Sea, known for its strategic military and commercial significance.
  • C. Samarobriva
    Samarobriva is the ancient Roman name for the city now known as Amiens in northern France, which served as an important settlement in Roman Gaul.
  • D. Singidunum
    Singidunum was the ancient Roman and earlier Celtic settlement that occupied the site of present-day Belgrade, Serbia.
  • E. Emona
    Emona is a small coastal settlement on Bulgaria’s Black Sea coast, situated close to Cape Emine.
  • 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_69ca82f64c188190af4e1608036b865d completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb80c229708190b813f5e7e44e10d4 completed March 31, 2026, 8:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69cde7fa87908190a504f8aaae125a7a completed April 2, 2026, 3:52 a.m.
Created at: March 30, 2026, 6:02 p.m.