Triple

T21866746
Position Surface form Disambiguated ID Type / Status
Subject Regio I Porta Capena E539900 entity
Predicate contains P35 FINISHED
Object Via Sinuessa Nova 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: Via Sinuessa Nova | Statement: [Regio I Porta Capena, contains, Via Sinuessa Nova]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Via Sinuessa Nova
Context triple: [Regio I Porta Capena, contains, Via Sinuessa Nova]
  • A. Via Sinuessa chosen
    Via Sinuessa was an ancient Roman road leading toward the coastal town of Sinuessa, serving as part of the broader network of routes connecting Rome with southern Italy.
  • B. Via Po
    Via Po is one of Turin’s main historic streets, running from Piazza Castello toward the River Po and lined with arcades, shops, and cafés.
  • C. Via Laurentina
    Via Laurentina is an ancient Roman road that linked the city of Rome with the Latin town of Lavinium in the region of Latium.
  • D. Via Sebaste
    Via Sebaste was a major Roman road in the province of Galatia that connected key cities in Pisidia and surrounding regions, facilitating military movement and trade.
  • E. Via Labicana
    Via Labicana is an ancient Roman road that connected Rome to the town of Labicum and served as a significant route lined with monuments and suburban developments.
  • 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_69f0f331c55c8190b73cb5aec3378a9e completed April 28, 2026, 5:49 p.m.
Created at: April 16, 2026, 6:56 p.m.