Triple

T9960544
Position Surface form Disambiguated ID Type / Status
Subject Sunjong of Korea E195555 entity
Predicate eraName P2938 FINISHED
Object Yunghui E193591 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: Yunghui | Statement: [Sunjong of Korea, eraName, Yunghui]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yunghui
Context triple: [Sunjong of Korea, eraName, Yunghui]
  • A. Yunghui chosen
    Yunghui was the final era name of the Korean Empire, marking its last years before annexation by Japan in the early 20th century.
  • B. Shuheng
    Shuheng is the given name of He Shuheng, an early Chinese Communist revolutionary and political figure.
  • C. Zhihong
    Zhihong is a Chinese given name that represents an alternative romanization of the name Zhizhong.
  • D. Dong Yun
    Dong Yun was a prominent Shu Han statesman of the Three Kingdoms period, known for his integrity and influence as a close advisor to Emperor Liu Shan.
  • E. Haad Yuan
    Haad Yuan is a small, secluded beach on Thailand’s Ko Pha Ngan island, known for its tranquil atmosphere, clear waters, and relaxed, off-the-beaten-path vibe.
  • 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_69ca82eaaa008190a54fa1a9f954b9ad completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb6d219c48190b2084b0eb07ae125 completed April 2, 2026, 12:22 a.m.
NED1 Entity disambiguation (via context triple) batch_69d23d867b408190ab630ae4af0fb827 completed April 5, 2026, 10:46 a.m.
Created at: March 30, 2026, 8:47 p.m.