Triple

T2873242
Position Surface form Disambiguated ID Type / Status
Subject Arakan E56814 entity
Predicate historicalCapital P2536 FINISHED
Object Vesali
Vesali was an ancient city that served as a major early capital and cultural center of the Arakan (Rakhine) region in present-day Myanmar.
 E304683 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: Vesali | Statement: [Arakan, historicalCapital, Vesali]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Vesali
Context triple: [Arakan, historicalCapital, Vesali]
  • A. Vallettan
    Vallettan is the demonym for a resident or native of Valletta, the capital city of Malta.
  • B. Balzar
    Balzar is a town and agricultural center in coastal Ecuador, known for its rice and banana production within Guayas Province.
  • C. Veneti
    The Veneti were an ancient people of northeastern Italy, known from Roman sources for their distinct language, culture, and interactions with neighboring Celtic and Italic groups.
  • D. Hoschedé
    Hoschedé is a French surname notably associated with the family closely linked to Impressionist painter Claude Monet.
  • E. Menetes
    Menetes is a genus of rodents in the squirrel family, comprising ground-dwelling squirrels native to parts of Asia.
  • 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: Vesali
Triple: [Arakan, historicalCapital, Vesali]
Generated description
Vesali was an ancient city that served as a major early capital and cultural center of the Arakan (Rakhine) region in present-day Myanmar.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Vesali
Target entity description: Vesali was an ancient city that served as a major early capital and cultural center of the Arakan (Rakhine) region in present-day Myanmar.
  • A. Vallettan
    Vallettan is the demonym for a resident or native of Valletta, the capital city of Malta.
  • B. Balzar
    Balzar is a town and agricultural center in coastal Ecuador, known for its rice and banana production within Guayas Province.
  • C. Veneti
    The Veneti were an ancient people of northeastern Italy, known from Roman sources for their distinct language, culture, and interactions with neighboring Celtic and Italic groups.
  • D. Hoschedé
    Hoschedé is a French surname notably associated with the family closely linked to Impressionist painter Claude Monet.
  • E. Menetes
    Menetes is a genus of rodents in the squirrel family, comprising ground-dwelling squirrels native to parts of Asia.
  • 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_69ab4a4ced288190ab6d3e062d10f7f6 completed March 6, 2026, 9:42 p.m.
NER Named-entity recognition batch_69abdfe59ef88190b8bdfdd03e8965f3 completed March 7, 2026, 8:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69b01db40e388190a208fe58e2ed6029 completed March 10, 2026, 1:33 p.m.
NEDg Description generation batch_69b01f8745948190b4821aac1941276c completed March 10, 2026, 1:41 p.m.
NED2 Entity disambiguation (via description) batch_69b020482e548190ab837025540673f7 completed March 10, 2026, 1:44 p.m.
Created at: March 6, 2026, 10:03 p.m.