Triple

T217485
Position Surface form Disambiguated ID Type / Status
Subject Vietnam E4138 entity
Predicate capital P234 FINISHED
Object Hanoi E6204 NE FINISHED

How this triple was built (2 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: Hanoi | Statement: [Vietnam, capital, Hanoi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hanoi
Context triple: [Vietnam, capital, Hanoi]
  • A. Hanoi chosen
    Hanoi is the historic and modern capital of Vietnam, known for its centuries-old architecture, rich cultural heritage, and vibrant street life.
  • B. Saigon
    Saigon, now officially known as Ho Chi Minh City, is Vietnam’s largest city and a historic economic and cultural hub in the south of the country.
  • C. Bangkok
    Bangkok is the vibrant capital and largest city of Thailand, known for its bustling street life, ornate temples, and role as a major economic and cultural hub in Southeast Asia.
  • D. Pyongyang
    Pyongyang is the capital and largest city of North Korea, serving as its political, economic, and cultural center.
  • E. Taipei, Taiwan
    Taipei, Taiwan is the capital and largest city of Taiwan, known as a major political, economic, and cultural center in East Asia.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a2573508588190b522c2476d91acfe completed Feb. 28, 2026, 2:47 a.m.
NER Named-entity recognition batch_69a25c5062e48190833be10e4770e1e9 completed Feb. 28, 2026, 3:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69a3441e48b48190849c7bff04134ac9 completed Feb. 28, 2026, 7:38 p.m.
Created at: Feb. 28, 2026, 2:53 a.m.