Triple

T1183582
Position Surface form Disambiguated ID Type / Status
Subject Roman Forum E25194 entity
Predicate contains P35 FINISHED
Object Via Sacra E42847 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: Via Sacra | Statement: [Roman Forum, contains, Via Sacra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Via Sacra
Context triple: [Roman Forum, contains, Via Sacra]
  • A. Via Sacra chosen
    Via Sacra was the main ceremonial street of ancient Rome, running through the Roman Forum and used for triumphal processions and public religious events.
  • B. Via Ostiense
    Via Ostiense is a historic road in Rome that connects the city center to the Basilica of Saint Paul Outside the Walls and the ancient port of Ostia.
  • C. Via Appia
    Via Appia is one of the earliest and most important ancient Roman roads, historically serving as a major route connecting Rome to southern Italy.
  • D. Via Aurelia
    Via Aurelia was an important ancient Roman road that ran along the Tyrrhenian coast of Italy, connecting Rome with key cities in Etruria and beyond.
  • E. Via Flaminia
    Via Flaminia was a major ancient Roman consular road that connected Rome to the Adriatic Sea, serving as a crucial route for military, commercial, and administrative travel in central Italy.
  • 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_69a494267b4c819088c97a59182bf56a completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4bd37b4a88190bb71a2d272c5fd1a completed March 1, 2026, 10:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac6f21547c81909cf23c454436e839 completed March 7, 2026, 6:32 p.m.
Created at: March 1, 2026, 7:45 p.m.