Triple

T13165630
Position Surface form Disambiguated ID Type / Status
Subject Germania Inferior E312841 entity
Predicate currencyUsed P188 FINISHED
Object Roman denarius E753342 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: Roman denarius | Statement: [Germania Inferior, currencyUsed, Roman denarius]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roman denarius
Context triple: [Germania Inferior, currencyUsed, Roman denarius]
  • A. denarius chosen
    The denarius was a standard Roman silver coin that became the backbone of the Roman monetary system and a key medium of trade across the Roman world.
  • B. Roman sestertius
    The Roman sestertius was a large bronze coin of the Roman Empire, widely used in everyday transactions and notable for its detailed imperial portraits and propaganda imagery.
  • C. Follis
    The follis was a large bronze coin used in the Byzantine Empire, particularly prominent in the 6th and 7th centuries.
  • D. Aqua Antoniniana
    Aqua Antoniniana was an ancient Roman aqueduct built to supply water to the Baths of Caracalla in Rome.
  • E. Roman mint
    The Roman mint was the official facility in ancient Rome where the state produced its coinage, playing a central role in the empire’s economy and monetary policy.
  • 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_69d806ac3ee081909b2fd27d060aa974 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98c0bf5a48190bf245dceee24b579 completed April 10, 2026, 11:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6eaf6c9ec8190bc0097d62e57e52a completed May 3, 2026, 6:28 a.m.
Created at: April 9, 2026, 9:13 p.m.