Triple

T19529434
Position Surface form Disambiguated ID Type / Status
Subject Yemaek tribes E488619 entity
Predicate consideredAncestralTo P133657 FINISHED
Object Dongye
Dongye was an ancient Korean tribal state in northeastern Korea, known as one of the early polities that preceded and interacted with the Three Kingdoms.
 E1387871 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: Dongye | Statement: [Yemaek tribes, consideredAncestralTo, Dongye]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Dongye
Context triple: [Yemaek tribes, consideredAncestralTo, Dongye]
  • A. Dongye
    Dongye was the ancient capital city of the Minyue kingdom in what is now southeastern China.
  • B. Dongjum
    Dongjum is a small village in the province of Friesland in the northern Netherlands, known for its rural character and traditional Frisian landscape.
  • C. Gongjin
    Gongjin is the courtesy name of Zhou Yu, a renowned Eastern Han dynasty military general and strategist best known for his role in the Battle of Red Cliffs.
  • D. Sonchon
    Sonchon is a significant urban center in North Pyongan Province in northwestern North Korea, known for its administrative and regional economic role.
  • E. Seochon
    Seochon is a historic neighborhood in central Seoul known for its traditional hanok houses, narrow alleyways, and vibrant mix of old Korean culture and modern cafes and galleries.
  • 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: Dongye
Triple: [Yemaek tribes, consideredAncestralTo, Dongye]
Generated description
Dongye was an ancient Korean tribal state in northeastern Korea, known as one of the early polities that preceded and interacted with the Three Kingdoms.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Dongye
Target entity description: Dongye was an ancient Korean tribal state in northeastern Korea, known as one of the early polities that preceded and interacted with the Three Kingdoms.
  • A. Dongye
    Dongye was the ancient capital city of the Minyue kingdom in what is now southeastern China.
  • B. Dongjum
    Dongjum is a small village in the province of Friesland in the northern Netherlands, known for its rural character and traditional Frisian landscape.
  • C. Gongjin
    Gongjin is the courtesy name of Zhou Yu, a renowned Eastern Han dynasty military general and strategist best known for his role in the Battle of Red Cliffs.
  • D. Sonchon
    Sonchon is a significant urban center in North Pyongan Province in northwestern North Korea, known for its administrative and regional economic role.
  • E. Seochon
    Seochon is a historic neighborhood in central Seoul known for its traditional hanok houses, narrow alleyways, and vibrant mix of old Korean culture and modern cafes and galleries.
  • 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_69d8e8da8bec819081f400199491ccc3 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6363dfd6c8190aaa0b374184965bb completed April 20, 2026, 2:20 p.m.
NED1 Entity disambiguation (via context triple) batch_6a077ed3473c8190a506642244eb2987 completed May 15, 2026, 8:15 p.m.
NEDg Description generation batch_6a077f87d96c8190a8d9ee82e84be1f2 completed May 15, 2026, 8:18 p.m.
NED2 Entity disambiguation (via description) batch_6a07816f54408190b6458ed0d17f9b60 completed May 15, 2026, 8:26 p.m.
Created at: April 10, 2026, 1:41 p.m.