Triple

T20588460
Position Surface form Disambiguated ID Type / Status
Subject Later Baekje E505849 entity
Predicate ruler P403 FINISHED
Object Singyeong
Singyeong was a monarch of the Later Baekje kingdom during Korea’s Later Three Kingdoms period.
 E1440357 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: Singyeong | Statement: [Later Baekje, ruler, Singyeong]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Singyeong
Context triple: [Later Baekje, ruler, Singyeong]
  • A. Ungnyeo
    Ungnyeo is a bear from Korean mythology who, after enduring a divine trial and transforming into a woman, became the ancestral mother of the Korean nation.
  • B. Junggyeong
    Junggyeong was one of the principal capital cities of the Balhae kingdom, serving as a key political and administrative center in Northeast Asia during the early medieval period.
  • C. Hyeonreung
    Hyeonreung is a royal tomb from Korea’s Joseon Dynasty, notable as one of the UNESCO-listed burial sites of its kings and queens.
  • D. Jinwicheon
    Jinwicheon is a river flowing through the city of Pyeongtaek in South Korea.
  • E. Byeong-gi
    Byeong-gi is a supporting character in the South Korean series "Squid Game," known as the doctor who secretly collaborates with corrupt guards to gain advantages in the deadly competition.
  • 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: Singyeong
Triple: [Later Baekje, ruler, Singyeong]
Generated description
Singyeong was a monarch of the Later Baekje kingdom during Korea’s Later Three Kingdoms period.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Singyeong
Target entity description: Singyeong was a monarch of the Later Baekje kingdom during Korea’s Later Three Kingdoms period.
  • A. Ungnyeo
    Ungnyeo is a bear from Korean mythology who, after enduring a divine trial and transforming into a woman, became the ancestral mother of the Korean nation.
  • B. Junggyeong
    Junggyeong was one of the principal capital cities of the Balhae kingdom, serving as a key political and administrative center in Northeast Asia during the early medieval period.
  • C. Hyeonreung
    Hyeonreung is a royal tomb from Korea’s Joseon Dynasty, notable as one of the UNESCO-listed burial sites of its kings and queens.
  • D. Jinwicheon
    Jinwicheon is a river flowing through the city of Pyeongtaek in South Korea.
  • E. Byeong-gi
    Byeong-gi is a supporting character in the South Korean series "Squid Game," known as the doctor who secretly collaborates with corrupt guards to gain advantages in the deadly competition.
  • 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.