Triple

T8226580
Position Surface form Disambiguated ID Type / Status
Subject Classis Moesica E192187 entity
Predicate garrisonLocation P40 FINISHED
Object Durostorum E217470 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: Durostorum | Statement: [Classis Moesica, garrisonLocation, Durostorum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Durostorum
Context triple: [Classis Moesica, garrisonLocation, Durostorum]
  • A. Durostorum chosen
    Durostorum was a major Roman military and urban center on the lower Danube, located in the province of Moesia (modern Silistra, Bulgaria).
  • B. Ulpia
    Ulpia is a Latin name element commonly associated with Roman imperial and colonial foundations, particularly linked to Emperor Trajan’s family name Ulpius.
  • C. Aurelianum
    Aurelianum is the ancient Latin name for the French city of Orléans, reflecting its origins as a Roman settlement.
  • D. Aquincum
    Aquincum was an important ancient Roman military and civilian settlement located in what is now northern Budapest, Hungary.
  • E. Carnuntum
    Carnuntum was a major Roman military camp and later a significant provincial capital and trading city on the Danube frontier in what is now eastern Austria.
  • 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_69ca82db5b90819085d1ad7c2e27bfcc completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb77fc10f48190b7e241c89885a478 completed March 31, 2026, 7:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69ccee140e708190bf07a63fecd08c7f completed April 1, 2026, 10:06 a.m.
Created at: March 30, 2026, 5:45 p.m.