Triple

T5572681
Position Surface form Disambiguated ID Type / Status
Subject Belu Regency E146239 entity
Predicate capital P234 FINISHED
Object Atambua
Atambua is a town in East Nusa Tenggara, Indonesia, located near the border with Timor-Leste and serving as an important regional trade and transit center.
 E531008 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: Atambua | Statement: [Belu Regency, capital, Atambua]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Atambua
Context triple: [Belu Regency, capital, Atambua]
  • A. Nacala
    Nacala is a coastal city in northern Mozambique known for its deep-water natural harbor and role as a major regional port and transport hub.
  • B. Tabora
    Tabora is a historic town in western Tanzania known as a regional trade center and former hub of 19th-century caravan routes.
  • C. Vilankulo
    Vilankulo is a coastal town in southern Mozambique known as the main gateway to the nearby Bazaruto Archipelago and its popular beach and marine tourism.
  • D. Limbe
    Limbe is a coastal city in southwestern Cameroon known for its black sand beaches, oil industry, and cultural diversity.
  • E. Anjara
    Anjara is a town in northern Jordan situated within the hilly, forested region of Ajloun, known for its Christian pilgrimage sites and scenic landscapes.
  • 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: Atambua
Triple: [Belu Regency, capital, Atambua]
Generated description
Atambua is a town in East Nusa Tenggara, Indonesia, located near the border with Timor-Leste and serving as an important regional trade and transit center.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Atambua
Target entity description: Atambua is a town in East Nusa Tenggara, Indonesia, located near the border with Timor-Leste and serving as an important regional trade and transit center.
  • A. Nacala
    Nacala is a coastal city in northern Mozambique known for its deep-water natural harbor and role as a major regional port and transport hub.
  • B. Tabora
    Tabora is a historic town in western Tanzania known as a regional trade center and former hub of 19th-century caravan routes.
  • C. Vilankulo
    Vilankulo is a coastal town in southern Mozambique known as the main gateway to the nearby Bazaruto Archipelago and its popular beach and marine tourism.
  • D. Limbe
    Limbe is a coastal city in southwestern Cameroon known for its black sand beaches, oil industry, and cultural diversity.
  • E. Anjara
    Anjara is a town in northern Jordan situated within the hilly, forested region of Ajloun, known for its Christian pilgrimage sites and scenic landscapes.
  • 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_69c008ffed108190a084602227af6157 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c020518f348190879ac67dab307134 completed March 22, 2026, 5:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0284ef6e48190bae9c9a1b1d77f5d completed March 22, 2026, 5:35 p.m.
NEDg Description generation batch_69c037b5be3c819098c8500350267a1e completed March 22, 2026, 6:40 p.m.
NED2 Entity disambiguation (via description) batch_69c0393144248190a97d1f82b81cc868 completed March 22, 2026, 6:47 p.m.
Created at: March 22, 2026, 3:37 p.m.