Triple

T11065109
Position Surface form Disambiguated ID Type / Status
Subject Legio X Gemina E261602 entity
Predicate garrison P75 FINISHED
Object Aquincum E71316 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: Aquincum | Statement: [Legio X Gemina, garrison, Aquincum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aquincum
Context triple: [Legio X Gemina, garrison, Aquincum]
  • A. Aquincum chosen
    Aquincum was an important ancient Roman military and civilian settlement located in what is now northern Budapest, Hungary.
  • B. Argentoratum
    Argentoratum is the ancient Roman military camp and settlement that later developed into the modern city of Strasbourg in northeastern France.
  • C. Durostorum
    Durostorum was a major Roman military and urban center on the lower Danube, located in the province of Moesia (modern Silistra, Bulgaria).
  • D. Mogontiacum
    Mogontiacum was the major Roman military and administrative settlement that later developed into the modern German city of Mainz.
  • 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_69d6aa98650481908609c7c56bfa7902 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d798edcab881909da1ba0394020ef8 completed April 9, 2026, 12:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3c8977f98819082dec025e92782da completed April 18, 2026, 6:08 p.m.
Created at: April 8, 2026, 9:26 p.m.