Triple

T20588457
Position Surface form Disambiguated ID Type / Status
Subject Later Baekje E505849 entity
Predicate capital P234 FINISHED
Object Wansanju
Wansanju was an important city in the Korean peninsula that served as the political and administrative center of the Later Baekje kingdom during the Later Three Kingdoms period.
 E1440356 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: Wansanju | Statement: [Later Baekje, capital, Wansanju]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Wansanju
Context triple: [Later Baekje, capital, Wansanju]
  • A. Wansin
    Wansin is a village in the municipality of Hannut in the province of Liège, Belgium.
  • B. Yakusho
    Yakusho is the family name of acclaimed Japanese actor Kōji Yakusho, known for his prominent roles in both Japanese and international cinema.
  • C. Owariasahi
    Owariasahi is a suburban city in central Japan known for its residential communities and proximity to Nagoya in Aichi Prefecture.
  • D. Chinnaru
    Chinnaru is a minor tributary river that feeds into the Noyyal River in the Indian state of Tamil Nadu.
  • E. Taketa
    Taketa is a small historic city in Japan known for its scenic rural landscapes, hot springs, and castle ruins.
  • 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: Wansanju
Triple: [Later Baekje, capital, Wansanju]
Generated description
Wansanju was an important city in the Korean peninsula that served as the political and administrative center of the Later Baekje kingdom during the Later Three Kingdoms period.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Wansanju
Target entity description: Wansanju was an important city in the Korean peninsula that served as the political and administrative center of the Later Baekje kingdom during the Later Three Kingdoms period.
  • A. Wansin
    Wansin is a village in the municipality of Hannut in the province of Liège, Belgium.
  • B. Yakusho
    Yakusho is the family name of acclaimed Japanese actor Kōji Yakusho, known for his prominent roles in both Japanese and international cinema.
  • C. Owariasahi
    Owariasahi is a suburban city in central Japan known for its residential communities and proximity to Nagoya in Aichi Prefecture.
  • D. Chinnaru
    Chinnaru is a minor tributary river that feeds into the Noyyal River in the Indian state of Tamil Nadu.
  • E. Taketa
    Taketa is a small historic city in Japan known for its scenic rural landscapes, hot springs, and castle ruins.
  • 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_69e0b4b9669c8190b8e81fc72817d42c completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a9790cc08190b48949834cd421d2 completed April 20, 2026, 10:32 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08b3e61f888190b805b7d19d673536 completed May 16, 2026, 6:13 p.m.
NEDg Description generation batch_6a08b4a7779481909b5bf6e99e632841 completed May 16, 2026, 6:17 p.m.
NED2 Entity disambiguation (via description) batch_6a08b57ff3e48190952c973726821e2b completed May 16, 2026, 6:20 p.m.
Created at: April 16, 2026, 11:40 a.m.