Triple

T20413217
Position Surface form Disambiguated ID Type / Status
Subject Jumong E500641 entity
Predicate name P16 FINISHED
Object Jumong NE NERFINISHED

How this triple was built (2 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: Jumong | Statement: [Jumong, name, Jumong]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jumong
Context triple: [Jumong, name, Jumong]
  • A. Jumong chosen
    Jumong is the legendary founder and first king of the ancient Korean kingdom of Goguryeo, celebrated as a heroic archer and culture hero in Korean history and mythology.
  • B. Hyeokgeose of Silla
    Hyeokgeose of Silla was the legendary founder and first king of the ancient Korean kingdom of Silla, traditionally said to have established the state in 57 BCE.
  • C. Bak Hyeokgeose
    Bak Hyeokgeose was the legendary first king of Silla, one of Korea’s Three Kingdoms, traditionally credited with establishing its royal dynasty in the 1st century BCE.
  • D. Gyeongsun of Silla
    Gyeongsun of Silla was the final king of the Korean kingdom of Silla, whose reign marked the end of the ancient Three Kingdoms period legacy and the kingdom’s absorption into Goryeo.
  • E. Gyeongmyeong of Silla
    Gyeongmyeong of Silla was a monarch of the Korean kingdom of Silla who ruled during its later period amid political decline and regional fragmentation.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4a935588190b9446a99b37ced44 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e67a417f208190be9bc11650ee0a87 completed April 20, 2026, 7:10 p.m.
Created at: April 16, 2026, 11:30 a.m.