Triple

T20646129
Position Surface form Disambiguated ID Type / Status
Subject Hall of Worthies E507359 entity
Predicate significantFigure P428 FINISHED
Object Ha Wi-ji
Ha Wi-ji was a prominent Joseon Dynasty scholar-official associated with the royal research institution known as the Hall of Worthies.
E1442607 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: Ha Wi-ji | Statement: [Hall of Worthies, significantFigure, Ha Wi-ji]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ha Wi-ji
Context triple: [Hall of Worthies, significantFigure, Ha Wi-ji]
  • A. Hwangje
    Hwangje is the Korean imperial title corresponding to the Chinese sovereign known as the Yellow Emperor (Huangdi).
  • B. Huaiji
    Huaiji is a county in Guangdong Province, China, known historically as the ancestral home of the Yang clan.
  • C. Hongshi
    Hongshi was an era name used during the Later Yan dynasty in ancient China, marking a specific reign period in its imperial chronology.
  • D. Houcong
    Houcong is the given name of Zhu Houcong, better known as the Jiajing Emperor of China’s Ming dynasty.
  • E. Yi Ti
    Yi Ti is a vast, wealthy, and ancient eastern empire in the world of A Song of Ice and Fire, renowned for its opulence, elaborate courts, and rich history that rivals Valyria in age and grandeur.
  • 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: Ha Wi-ji
Triple: [Hall of Worthies, significantFigure, Ha Wi-ji]
Generated description
Ha Wi-ji was a prominent Joseon Dynasty scholar-official associated with the royal research institution known as the Hall of Worthies.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ha Wi-ji
Target entity description: Ha Wi-ji was a prominent Joseon Dynasty scholar-official associated with the royal research institution known as the Hall of Worthies.
  • A. Hwangje
    Hwangje is the Korean imperial title corresponding to the Chinese sovereign known as the Yellow Emperor (Huangdi).
  • B. Huaiji
    Huaiji is a county in Guangdong Province, China, known historically as the ancestral home of the Yang clan.
  • C. Hongshi
    Hongshi was an era name used during the Later Yan dynasty in ancient China, marking a specific reign period in its imperial chronology.
  • D. Houcong
    Houcong is the given name of Zhu Houcong, better known as the Jiajing Emperor of China’s Ming dynasty.
  • E. Yi Ti
    Yi Ti is a vast, wealthy, and ancient eastern empire in the world of A Song of Ice and Fire, renowned for its opulence, elaborate courts, and rich history that rivals Valyria in age and grandeur.
  • 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_69e0b4be702c8190a3d2410a881d310a completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6af1eee9c81908fd3b4fe8c4529c8 completed April 20, 2026, 10:56 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08c58e9b0081908fd2c4f3d8022401 completed May 16, 2026, 7:29 p.m.
NEDg Description generation batch_6a08c65993408190859c75fb65ade257 completed May 16, 2026, 7:32 p.m.
NED2 Entity disambiguation (via description) batch_6a08c78fe4d48190a7a69f65f64ac66c completed May 16, 2026, 7:37 p.m.
Created at: April 16, 2026, 11:43 a.m.