Triple

T2148510
Position Surface form Disambiguated ID Type / Status
Subject Bantia E47124 entity
Predicate modernSiteNear P8489 FINISHED
Object Banzi
Banzi is a town in the Basilicata region of southern Italy, known as the modern site near the ancient Lucanian city of Bantia.
 E238962 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: Banzi | Statement: [Bantia, modernSiteNear, Banzi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Banzi
Context triple: [Bantia, modernSiteNear, Banzi]
  • A. Cobi
    Cobi is the cubist-style Catalan sheepdog character that served as the official mascot of the 1992 Barcelona Summer Olympics.
  • B. Bubi
    Bubi is a Bantu language spoken by the Bubi people, primarily on Bioko Island in Equatorial Guinea.
  • C. Bubi
    Bubi is the nickname of Erich Hartmann, the German World War II fighter pilot who became history’s highest-scoring flying ace.
  • D. Ziro
    Ziro is a picturesque valley town in northeastern India known for its Apatani tribal culture, rice fields, and the annual Ziro Music Festival.
  • E. Borobi
    Borobi is a blue koala character created as the official mascot for the 2018 Commonwealth Games held on Australia's Gold Coast.
  • 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: Banzi
Triple: [Bantia, modernSiteNear, Banzi]
Generated description
Banzi is a town in the Basilicata region of southern Italy, known as the modern site near the ancient Lucanian city of Bantia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Banzi
Target entity description: Banzi is a town in the Basilicata region of southern Italy, known as the modern site near the ancient Lucanian city of Bantia.
  • A. Cobi
    Cobi is the cubist-style Catalan sheepdog character that served as the official mascot of the 1992 Barcelona Summer Olympics.
  • B. Bubi
    Bubi is the nickname of Erich Hartmann, the German World War II fighter pilot who became history’s highest-scoring flying ace.
  • C. Bubi
    Bubi is a Bantu language spoken by the Bubi people, primarily on Bioko Island in Equatorial Guinea.
  • D. Ziro
    Ziro is a picturesque valley town in northeastern India known for its Apatani tribal culture, rice fields, and the annual Ziro Music Festival.
  • E. Borobi
    Borobi is a blue koala character created as the official mascot for the 2018 Commonwealth Games held on Australia's Gold Coast.
  • 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_69a88a1933e0819094f18426ed74180f completed March 4, 2026, 7:38 p.m.
NER Named-entity recognition batch_69abbe44d2608190986467d43ee224d4 completed March 7, 2026, 5:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae58d9c52081909f6acb0558369310 completed March 9, 2026, 5:21 a.m.
NEDg Description generation batch_69ae59892b848190a9cc8b086647ff14 completed March 9, 2026, 5:24 a.m.
NED2 Entity disambiguation (via description) batch_69ae5a02404c819088acf7c592cb2cae completed March 9, 2026, 5:26 a.m.
Created at: March 4, 2026, 7:44 p.m.