Triple

T8227491
Position Surface form Disambiguated ID Type / Status
Subject Remi E192207 entity
Predicate administrativeCenter P1474 FINISHED
Object Durocortorum E585927 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: Durocortorum | Statement: [Remi, administrativeCenter, Durocortorum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Durocortorum
Context triple: [Remi, administrativeCenter, Durocortorum]
  • A. Durocortorum chosen
    Durocortorum was an important Roman city in northeastern Gaul, known today as Reims in France.
  • B. Duranus
    Duranus is a small rural commune in southeastern France, located in the Alpes-Maritimes department in the Provence-Alpes-Côte d’Azur region.
  • C. Noviodunum
    Noviodunum was an important Roman military and naval base on the lower Danube, in the province of Moesia (modern-day Romania).
  • D. Albingaunum
    Albingaunum is the ancient Roman name for the Ligurian coastal town now known as Albenga in northwestern Italy.
  • E. Dacia Ripensis
    Dacia Ripensis was a late Roman province along the Danube frontier in the Balkans, known as a militarized border region of the 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_69ca82db5b90819085d1ad7c2e27bfcc completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb77fdcb048190868ea4995b020a37 completed March 31, 2026, 7:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd67ec97348190a1ae7fc8d30af838 completed April 1, 2026, 6:46 p.m.
Created at: March 30, 2026, 5:46 p.m.