Triple

T23010416
Position Surface form Disambiguated ID Type / Status
Subject Ambiani E572889 entity
Predicate capital P234 FINISHED
Object Samarobriva NE NERFINISHED

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: Samarobriva | Statement: [Ambiani, capital, Samarobriva]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Samarobriva
Context triple: [Ambiani, capital, Samarobriva]
  • A. Samarobriva chosen
    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.
  • B. Ambracia
    Ambracia was an ancient Greek city in Epirus that became an important regional center and later the capital of King Pyrrhus.
  • C. Brundisium
    Brundisium was an important ancient Roman port city in southern Italy, strategically located on the Adriatic Sea and serving as a major gateway to the eastern Mediterranean.
  • D. Gradara
    Gradara is a medieval hilltop town in Italy’s Marche region, renowned for its well-preserved castle and association with the tragic love story of Paolo and Francesca.
  • E. Oropus
    Oropus was an ancient Greek town on the border of Attica and Boeotia, best known for its sanctuary and oracle of the hero Amphiaraus.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e245b764cc8190a51be76f1d9611e1 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18359f5548190b15a139eb09e30a0 completed April 29, 2026, 4:04 a.m.
Created at: April 17, 2026, 3:51 p.m.