Triple

T21865889
Position Surface form Disambiguated ID Type / Status
Subject Aqua Virgo E539880 entity
Predicate hasItalianName P17612 FINISHED
Object Acqua Vergine 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: Acqua Vergine | Statement: [Aqua Virgo, hasItalianName, Acqua Vergine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Acqua Vergine
Context triple: [Aqua Virgo, hasItalianName, Acqua Vergine]
  • A. Acqua Vergine chosen
    Acqua Vergine is a historic Roman aqueduct system, still in use today, that supplies water to several famous fountains in Rome, including the Trevi Fountain.
  • B. Cisterna di Latina
    Cisterna di Latina is a town and comune in the Lazio region of central Italy, known for its agricultural production and proximity to the Pontine Marshes.
  • C. Aquae Sextiae
    Aquae Sextiae was the ancient Roman settlement and spa town that later became the modern city of Aix-en-Provence in southern France.
  • D. Aqua Appia
    Aqua Appia was one of ancient Rome’s earliest aqueducts, constructed in the 4th century BCE to supply the city with fresh water.
  • E. Lanuvium
    Lanuvium was an ancient Latin city in central Italy, noted for its important sanctuary of Juno Sospita and its later incorporation into the Roman state.
  • 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_69e0c478f59081909d54302b57fc1ce3 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f0d63f2ec48190956a3e99d8f98b1f completed April 28, 2026, 3:46 p.m.
Created at: April 16, 2026, 6:56 p.m.