Triple

T14006830
Position Surface form Disambiguated ID Type / Status
Subject Via Severiana E336970 entity
Predicate endPoint P390 FINISHED
Object Terracina E339378 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: Terracina | Statement: [Via Severiana, endPoint, Terracina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Terracina
Context triple: [Via Severiana, endPoint, Terracina]
  • A. Terracina chosen
    Terracina is a historic coastal city in the Lazio region of central Italy, known for its ancient Roman ruins and scenic position on the Tyrrhenian Sea.
  • B. Velletri
    Velletri is a historic town in the Lazio region of central Italy, known for its ancient Roman roots, wine production, and location in the Alban Hills southeast of Rome.
  • C. Minturno
    Minturno is a historic town in the Lazio region of central Italy, known for its ancient Roman ruins and scenic position near the Tyrrhenian coast.
  • D. Sermoneta
    Sermoneta is a historic hilltop town in Italy’s Lazio region, renowned for its well-preserved medieval architecture and imposing Caetani Castle.
  • E. Arpino
    Arpino is a historic town in central Italy, traditionally known as the birthplace of the Roman statesman Cicero.
  • 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_69d81c645c5c8190b1fd16a285a1b78a completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2ed327d88190a53af5768468a8eb completed April 14, 2026, 12:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbc329891c8190b4dcb9913e235a1c completed May 6, 2026, 10:39 p.m.
Created at: April 9, 2026, 10:19 p.m.