Triple

T6845276
Position Surface form Disambiguated ID Type / Status
Subject Province of Terni E157878 entity
Predicate contains P35 FINISHED
Object San Gemini
San Gemini is a historic medieval hill town in central Italy’s Umbria region, renowned for its mineral springs and well-preserved architecture.
E623013 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: San Gemini | Statement: [Province of Terni, contains, San Gemini]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: San Gemini
Context triple: [Province of Terni, contains, San Gemini]
  • A. Torrenova
    Torrenova is a coastal resort area on the island of Mallorca in Spain, known for its beaches and proximity to the nightlife of Magaluf.
  • B. Samario
    Samario is the Spanish demonym for a person from the city of Santa Marta in Colombia.
  • C. Muribeca
    Muribeca is a municipality in the Brazilian state of Sergipe, known for its rural character within the semi-arid interior region.
  • D. San Diu
    San Diu are an ethnic minority group in northern Vietnam, known for their distinct language, folk songs, and cultural traditions influenced by both Vietnamese and southern Chinese heritage.
  • E. Thaton
    Thaton is an ancient city in southern Myanmar historically significant as a major center of the Mon kingdom and Theravada Buddhism in the region.
  • 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: San Gemini
Triple: [Province of Terni, contains, San Gemini]
Generated description
San Gemini is a historic medieval hill town in central Italy’s Umbria region, renowned for its mineral springs and well-preserved architecture.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: San Gemini
Target entity description: San Gemini is a historic medieval hill town in central Italy’s Umbria region, renowned for its mineral springs and well-preserved architecture.
  • A. Torrenova
    Torrenova is a coastal resort area on the island of Mallorca in Spain, known for its beaches and proximity to the nightlife of Magaluf.
  • B. Samario
    Samario is the Spanish demonym for a person from the city of Santa Marta in Colombia.
  • C. Muribeca
    Muribeca is a municipality in the Brazilian state of Sergipe, known for its rural character within the semi-arid interior region.
  • D. San Diu
    San Diu are an ethnic minority group in northern Vietnam, known for their distinct language, folk songs, and cultural traditions influenced by both Vietnamese and southern Chinese heritage.
  • E. Thaton
    Thaton is an ancient city in southern Myanmar historically significant as a major center of the Mon kingdom and Theravada Buddhism in the region.
  • 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_69c6882ed4c081909dc465a7cf8838be completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d7ca96008190ba79563c2a9a9b0e completed March 27, 2026, 7:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69c72fc42e688190baa8413883e5506c completed March 28, 2026, 1:32 a.m.
NEDg Description generation batch_69c7304c0bac8190a9ece4e50ab49586 completed March 28, 2026, 1:35 a.m.
NED2 Entity disambiguation (via description) batch_69c7310fa9bc8190bfb0a43890dc5e96 completed March 28, 2026, 1:38 a.m.
Created at: March 27, 2026, 2:19 p.m.