Triple

T23485601
Position Surface form Disambiguated ID Type / Status
Subject Trương Đình Dzu E570524 entity
Predicate opponent P437 FINISHED
Object Nguyễn Cao Kỳ NE NERFINISHED

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: Nguyễn Cao Kỳ | Statement: [Trương Đình Dzu, opponent, Nguyễn Cao Kỳ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nguyễn Cao Kỳ
Context triple: [Trương Đình Dzu, opponent, Nguyễn Cao Kỳ]
  • A. Nguyễn Cao Kỳ chosen
    Nguyễn Cao Kỳ was a prominent South Vietnamese military officer and politician who served as prime minister and later vice president during the Vietnam War era.
  • B. Nguyễn Chánh Thi
    Nguyễn Chánh Thi was a prominent South Vietnamese lieutenant general and influential I Corps commander during the Vietnam War, known for both his military leadership and political involvement in the mid-1960s.
  • C. Nguyễn Phi Khanh
    Nguyễn Phi Khanh was a Vietnamese Confucian scholar and official of the late Trần dynasty, best known as the father and early mentor of the great strategist and poet Nguyễn Trãi.
  • D. Văn Kỳ
    Văn Kỳ is a child of the renowned Vietnamese composer and poet Văn Cao.
  • E. Nguyễn Thị Hoàn
    Nguyễn Thị Hoàn was the mother of Emperor Gia Long, the founder of Vietnam’s Nguyễn dynasty.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e245b0b01481908f636939bedd804c completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a7538a8c8190b7effcc39a3f9787 completed April 29, 2026, 6:38 a.m.
Created at: April 17, 2026, 6:03 p.m.