Triple

T15090675
Position Surface form Disambiguated ID Type / Status
Subject Mongol invasion of Vietnam E360404 entity
Predicate commander P1061 FINISHED
Object Sogetu
Sogetu was a Yuan dynasty Mongol general best known for leading one of the major invasions of Đại Việt (medieval Vietnam) in the 13th century.
 E1136530 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: Sogetu | Statement: [Mongol invasion of Vietnam, commander, Sogetu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sogetu
Context triple: [Mongol invasion of Vietnam, commander, Sogetu]
  • A. Oka
    Oka is a small municipality in southwestern Quebec, Canada, known for its historic village, Oka National Park, and the famous Oka cheese produced by Trappist monks.
  • B. Wansin
    Wansin is a village in the municipality of Hannut in the province of Liège, Belgium.
  • C. Eonyang
    Eonyang is a town in South Korea that serves as the administrative and commercial center of Ulju County in Ulsan.
  • D. Owariasahi
    Owariasahi is a suburban city in central Japan known for its residential communities and proximity to Nagoya in Aichi Prefecture.
  • E. Ōta
    Ōta is a special ward in southern Tokyo, Japan, known for Haneda Airport and its mix of residential, industrial, and coastal areas.
  • 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: Sogetu
Triple: [Mongol invasion of Vietnam, commander, Sogetu]
Generated description
Sogetu was a Yuan dynasty Mongol general best known for leading one of the major invasions of Đại Việt (medieval Vietnam) in the 13th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sogetu
Target entity description: Sogetu was a Yuan dynasty Mongol general best known for leading one of the major invasions of Đại Việt (medieval Vietnam) in the 13th century.
  • A. Oka
    Oka is a small municipality in southwestern Quebec, Canada, known for its historic village, Oka National Park, and the famous Oka cheese produced by Trappist monks.
  • B. Wansin
    Wansin is a village in the municipality of Hannut in the province of Liège, Belgium.
  • C. Eonyang
    Eonyang is a town in South Korea that serves as the administrative and commercial center of Ulju County in Ulsan.
  • D. Owariasahi
    Owariasahi is a suburban city in central Japan known for its residential communities and proximity to Nagoya in Aichi Prefecture.
  • E. Ōta
    Ōta is a special ward in southern Tokyo, Japan, known for Haneda Airport and its mix of residential, industrial, and coastal areas.
  • 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_69d85a035aa88190b52a139d3a1b7b6d completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e00277ea808190be3f002a8316eff1 completed April 15, 2026, 9:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69feae1d7a0c819096b035f8ca8d0e90 completed May 9, 2026, 3:46 a.m.
NEDg Description generation batch_69feaf8e1b508190b0b5ceb64d44fad6 completed May 9, 2026, 3:52 a.m.
NED2 Entity disambiguation (via description) batch_69feb038065c8190b60266644db64092 completed May 9, 2026, 3:55 a.m.
Created at: April 10, 2026, 3:04 a.m.