Triple

T540392
Position Surface form Disambiguated ID Type / Status
Subject Lazio E12614 entity
Predicate containsCity P294 FINISHED
Object Viterbo
Viterbo is a historic city in central Italy known for its well-preserved medieval center, ancient thermal baths, and role as a papal residence in the 13th century.
 E103483 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: Viterbo | Statement: [Lazio, containsCity, Viterbo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Viterbo
Context triple: [Lazio, containsCity, Viterbo]
  • A. Cerveteri
    Cerveteri is an ancient Italian town best known as a powerful Etruscan city-state and for its extensive necropolis of rock-cut tombs.
  • B. San Savino
    San Savino is a small locality within the municipality of Predappio in the Emilia-Romagna region of northern Italy.
  • C. Frosinone
    Frosinone is a city in central Italy that serves as the capital of the province of the same name within the Lazio region.
  • D. Meldola
    Meldola is a small town in the Emilia-Romagna region of northern Italy, known for its historic center and proximity to the Apennine hills.
  • E. Assisi
    Assisi is an Italian hill town in Umbria renowned as the birthplace of St. Francis and a major center of Christian pilgrimage.
  • 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: Viterbo
Triple: [Lazio, containsCity, Viterbo]
Generated description
Viterbo is a historic city in central Italy known for its well-preserved medieval center, ancient thermal baths, and role as a papal residence in the 13th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Viterbo
Target entity description: Viterbo is a historic city in central Italy known for its well-preserved medieval center, ancient thermal baths, and role as a papal residence in the 13th century.
  • A. Cerveteri
    Cerveteri is an ancient Italian town best known as a powerful Etruscan city-state and for its extensive necropolis of rock-cut tombs.
  • B. San Savino
    San Savino is a small locality within the municipality of Predappio in the Emilia-Romagna region of northern Italy.
  • C. Frosinone
    Frosinone is a city in central Italy that serves as the capital of the province of the same name within the Lazio region.
  • D. Meldola
    Meldola is a small town in the Emilia-Romagna region of northern Italy, known for its historic center and proximity to the Apennine hills.
  • E. Assisi
    Assisi is an Italian hill town in Umbria renowned as the birthplace of St. Francis and a major center of Christian pilgrimage.
  • 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_69a49334226c81908b0ea1689ef6aa3f completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a4985feee481908184a39210feab95 completed March 1, 2026, 7:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7b830bf5c81908784e8146987eb96 completed March 4, 2026, 4:42 a.m.
NEDg Description generation batch_69a7ba8dd7408190b5ee7688e45f2473 completed March 4, 2026, 4:52 a.m.
NED2 Entity disambiguation (via description) batch_69a7bc1da490819097fe1e60e3e93ba4 completed March 4, 2026, 4:59 a.m.
Created at: March 1, 2026, 7:32 p.m.