Triple

T4537136
Position Surface form Disambiguated ID Type / Status
Subject Bar E107433 entity
Predicate historicalName P65 FINISHED
Object Antivari
Antivari is the historical Italian name for the coastal Montenegrin town of Bar, an important Adriatic port with a long and diverse cultural heritage.
 E450133 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: Antivari | Statement: [Bar, historicalName, Antivari]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Antivari
Context triple: [Bar, historicalName, Antivari]
  • A. Ante
    Ante is a masculine given name of Croatian origin, commonly used in various South Slavic countries.
  • B. Variyasi
    Variyasi is a figure in Hindu tradition known primarily as the daughter of Nanda, the foster father of Lord Krishna.
  • C. Vasi-vari
    Vasi-vari is an Indo-Iranian language spoken in parts of Afghanistan, more widely known as the Prasun language.
  • D. Antu
    Antu is one of the four 8.2-meter Unit Telescopes of the Very Large Telescope array operated by the European Southern Observatory at Paranal in Chile.
  • E. Antu
    Antu is a Mesopotamian sky and mother goddess, best known as the consort of the supreme god Anu in ancient Sumerian and Akkadian religion.
  • 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: Antivari
Triple: [Bar, historicalName, Antivari]
Generated description
Antivari is the historical Italian name for the coastal Montenegrin town of Bar, an important Adriatic port with a long and diverse cultural heritage.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Antivari
Target entity description: Antivari is the historical Italian name for the coastal Montenegrin town of Bar, an important Adriatic port with a long and diverse cultural heritage.
  • A. Ante
    Ante is a masculine given name of Croatian origin, commonly used in various South Slavic countries.
  • B. Variyasi
    Variyasi is a figure in Hindu tradition known primarily as the daughter of Nanda, the foster father of Lord Krishna.
  • C. Vasi-vari
    Vasi-vari is an Indo-Iranian language spoken in parts of Afghanistan, more widely known as the Prasun language.
  • D. Antu
    Antu is one of the four 8.2-meter Unit Telescopes of the Very Large Telescope array operated by the European Southern Observatory at Paranal in Chile.
  • E. Antu
    Antu is a Mesopotamian sky and mother goddess, best known as the consort of the supreme god Anu in ancient Sumerian and Akkadian religion.
  • 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_69bd43f922788190b7edfa294e39b178 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd57b78b8481909d79131723d4be22 completed March 20, 2026, 2:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdacfb2ba48190b7f1b23785e9d030 completed March 20, 2026, 8:24 p.m.
NEDg Description generation batch_69bdaf867740819090367e5ebd37b4d4 completed March 20, 2026, 8:35 p.m.
NED2 Entity disambiguation (via description) batch_69bdafeb5e0881909d4ee62b066dee91 completed March 20, 2026, 8:36 p.m.
Created at: March 20, 2026, 1:04 p.m.