Triple

T6563734
Position Surface form Disambiguated ID Type / Status
Subject SK Energy E153848 entity
Predicate formerName P65 FINISHED
Object Yukong
Yukong was the former name of SK Energy, a major South Korean petroleum and energy company within the SK Group conglomerate.
 E605534 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: Yukong | Statement: [SK Energy, formerName, Yukong]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Yukong
Context triple: [SK Energy, formerName, Yukong]
  • A. Gong Gong
    Gong Gong is the stern yet secretly caring grandfather in the film "Everything Everywhere All at Once," whose traditional values and hidden past shape the family’s emotional and multiversal conflicts.
  • B. Kangchungtse
    Kangchungtse is a high Himalayan subpeak of Mount Makalu located on the Nepal–Tibet border.
  • C. Zhenwu
    Zhenwu is a powerful Taoist deity associated with the north, martial protection, and spiritual cultivation, especially revered in Chinese religious and martial traditions.
  • D. Qiyu
    Qiyu was the personal name of the Jingtai Emperor, a 15th-century ruler of China's Ming dynasty.
  • E. Tian
    Tian is a Chinese given name commonly used for both males and females, often associated with meanings related to "sky" or "heaven."
  • 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: Yukong
Triple: [SK Energy, formerName, Yukong]
Generated description
Yukong was the former name of SK Energy, a major South Korean petroleum and energy company within the SK Group conglomerate.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Yukong
Target entity description: Yukong was the former name of SK Energy, a major South Korean petroleum and energy company within the SK Group conglomerate.
  • A. Gong Gong
    Gong Gong is the stern yet secretly caring grandfather in the film "Everything Everywhere All at Once," whose traditional values and hidden past shape the family’s emotional and multiversal conflicts.
  • B. Kangchungtse
    Kangchungtse is a high Himalayan subpeak of Mount Makalu located on the Nepal–Tibet border.
  • C. Zhenwu
    Zhenwu is a powerful Taoist deity associated with the north, martial protection, and spiritual cultivation, especially revered in Chinese religious and martial traditions.
  • D. Qiyu
    Qiyu was the personal name of the Jingtai Emperor, a 15th-century ruler of China's Ming dynasty.
  • E. Tian
    Tian is a Chinese given name commonly used for both males and females, often associated with meanings related to "sky" or "heaven."
  • 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_69c6880cb35881909b763eb0125236b9 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6ae3a40488190892d20ca0d60b937 completed March 27, 2026, 4:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6d5622e0481909b0ac0f4e06d19bc completed March 27, 2026, 7:07 p.m.
NEDg Description generation batch_69c6d82753288190bb8cd18254feee2d completed March 27, 2026, 7:19 p.m.
NED2 Entity disambiguation (via description) batch_69c6d92bc2508190b0e1eaf8b46c958e completed March 27, 2026, 7:23 p.m.
Created at: March 27, 2026, 1:52 p.m.