Triple

T8479899
Position Surface form Disambiguated ID Type / Status
Subject Lavinium E200487 entity
Predicate connectedByRoad P11435 FINISHED
Object 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.
 E737465 NE FINISHED

How this triple was built (4 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 Laurentina | Statement: [Lavinium, connectedByRoad, Via Laurentina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Via Laurentina
Context triple: [Lavinium, connectedByRoad, Via Laurentina]
  • A. 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.
  • 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 Severiana
    Via Severiana was an ancient Roman coastal road in Latium that linked several important seaside towns south of Rome.
  • D. Via Latina
    Via Latina was an important ancient Roman road that linked Rome with southern Italy, running through Latium and serving as a key military and commercial route.
  • E. Via Podiensis
    Via Podiensis is one of the main French pilgrimage routes of the Camino de Santiago, beginning in Le Puy-en-Velay and crossing southern France toward Spain.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Via Laurentina
Triple: [Lavinium, connectedByRoad, Via Laurentina]
Generated description
Via Laurentina is an ancient Roman road that linked the city of Rome with the Latin town of Lavinium in the region of Latium.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Via Laurentina
Target entity description: Via Laurentina is an ancient Roman road that linked the city of Rome with the Latin town of Lavinium in the region of Latium.
  • A. 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.
  • 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 Severiana
    Via Severiana was an ancient Roman coastal road in Latium that linked several important seaside towns south of Rome.
  • D. Via Latina
    Via Latina was an important ancient Roman road that linked Rome with southern Italy, running through Latium and serving as a key military and commercial route.
  • E. Via Podiensis
    Via Podiensis is one of the main French pilgrimage routes of the Camino de Santiago, beginning in Le Puy-en-Velay and crossing southern France toward Spain.
  • F. None of above. chosen

Provenance (5 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_69ca831b17988190a1f3f3413d57b820 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe5232d008190ae55b982f5fc9e8b completed March 31, 2026, 3:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce3a22d6e481908bdb0b9cc0df0113 completed April 2, 2026, 9:42 a.m.
NEDg Description generation batch_69ce3cddba648190be303823862a0423 completed April 2, 2026, 9:54 a.m.
NED2 Entity disambiguation (via description) batch_69ce3d5edabc8190b985546b8242e90a completed April 2, 2026, 9:56 a.m.
Created at: March 30, 2026, 6:12 p.m.