Triple

T11065110
Position Surface form Disambiguated ID Type / Status
Subject Legio X Gemina E261602 entity
Predicate garrison P75 FINISHED
Object Carnuntum E236032 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: Carnuntum | Statement: [Legio X Gemina, garrison, Carnuntum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carnuntum
Context triple: [Legio X Gemina, garrison, Carnuntum]
  • A. Carnuntum chosen
    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.
  • B. Aquincum
    Aquincum was an important ancient Roman military and civilian settlement located in what is now northern Budapest, Hungary.
  • 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. Singidunum
    Singidunum was the ancient Roman and earlier Celtic settlement that occupied the site of present-day Belgrade, Serbia.
  • E. Sirmium
    Sirmium was an important ancient Roman city in the province of Pannonia, serving as a major military, administrative, and imperial center in the late Roman Empire.
  • 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_69e3e75b90ec8190b1a799e0183c6784 completed April 18, 2026, 8:19 p.m.
Created at: April 8, 2026, 9:26 p.m.