Triple

T19701493
Position Surface form Disambiguated ID Type / Status
Subject North Hwanghae Province E473107 entity
Predicate hasCity P316 FINISHED
Object Songrim
Songrim is an industrial city in North Korea known for its steel production and location along the Taedong River.
E1391960 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: Songrim | Statement: [North Hwanghae Province, hasCity, Songrim]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Songrim
Context triple: [North Hwanghae Province, hasCity, Songrim]
  • A. Sijjin
    Sijjin is an Islamic term referring to a record or register in which the deeds of the wicked are inscribed and a place associated with severe punishment in the Hereafter.
  • B. Osancheon
    Osancheon is a river in Osan, South Korea, that flows through the city and serves as a local natural and recreational landmark.
  • C. Kum-song
    Kum-song is a Korean given name commonly used for both males and females.
  • D. Hwangje
    Hwangje is the Korean imperial title corresponding to the Chinese sovereign known as the Yellow Emperor (Huangdi).
  • E. Haeinsa
    Haeinsa is a renowned Korean Buddhist temple best known for housing the Tripitaka Koreana, the most complete extant collection of Buddhist scriptures carved onto wooden printing blocks.
  • 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: Songrim
Triple: [North Hwanghae Province, hasCity, Songrim]
Generated description
Songrim is an industrial city in North Korea known for its steel production and location along the Taedong River.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Songrim
Target entity description: Songrim is an industrial city in North Korea known for its steel production and location along the Taedong River.
  • A. Sijjin
    Sijjin is an Islamic term referring to a record or register in which the deeds of the wicked are inscribed and a place associated with severe punishment in the Hereafter.
  • B. Osancheon
    Osancheon is a river in Osan, South Korea, that flows through the city and serves as a local natural and recreational landmark.
  • C. Kum-song
    Kum-song is a Korean given name commonly used for both males and females.
  • D. Hwangje
    Hwangje is the Korean imperial title corresponding to the Chinese sovereign known as the Yellow Emperor (Huangdi).
  • E. Haeinsa
    Haeinsa is a renowned Korean Buddhist temple best known for housing the Tripitaka Koreana, the most complete extant collection of Buddhist scriptures carved onto wooden printing blocks.
  • 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_69d8e515bef88190bc30781aea50537a completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e642b667908190841bb5fb7bfdb3f7 completed April 20, 2026, 3:13 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07ab96a0d481908c044682919649fb completed May 15, 2026, 11:26 p.m.
NEDg Description generation batch_6a07ac41da0481909bb433c73ad2f656 completed May 15, 2026, 11:29 p.m.
NED2 Entity disambiguation (via description) batch_6a07acbd21308190babdc5b84ffe083d completed May 15, 2026, 11:31 p.m.
Created at: April 10, 2026, 1:46 p.m.