Triple

T10300324
Position Surface form Disambiguated ID Type / Status
Subject Anyang E241609 entity
Predicate hasNearbyMountain P651 FINISHED
Object Samseongsan
Samseongsan is a mountain in South Korea known for its hiking trails and views over the Anyang and southern Seoul metropolitan area.
E856392 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: Samseongsan | Statement: [Anyang, hasNearbyMountain, Samseongsan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Samseongsan
Context triple: [Anyang, hasNearbyMountain, Samseongsan]
  • A. Namsan
    Namsan is a prominent central mountain in Seoul, South Korea, known for its panoramic city views and the iconic N Seoul Tower.
  • B. N Seoul Tower
    N Seoul Tower is a prominent communication and observation tower on Namsan Mountain that serves as one of Seoul’s most recognizable cityscape landmarks and tourist attractions.
  • C. Ok-dong
    Ok-dong is a neighborhood in Ulsan, South Korea, known for encompassing the large urban green space of Ulsan Grand Park.
  • D. Seongsan Ilchulbong
    Seongsan Ilchulbong is a dramatic tuff cone crater on the eastern coast of Jeju Island in South Korea, famed for its sunrise views and unique volcanic landscape.
  • E. Baegunsan
    Baegunsan is a mountain located in or near the city of Uiwang in South Korea, known for its hiking trails and natural scenery.
  • 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: Samseongsan
Triple: [Anyang, hasNearbyMountain, Samseongsan]
Generated description
Samseongsan is a mountain in South Korea known for its hiking trails and views over the Anyang and southern Seoul metropolitan area.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Samseongsan
Target entity description: Samseongsan is a mountain in South Korea known for its hiking trails and views over the Anyang and southern Seoul metropolitan area.
  • A. Namsan
    Namsan is a prominent central mountain in Seoul, South Korea, known for its panoramic city views and the iconic N Seoul Tower.
  • B. N Seoul Tower
    N Seoul Tower is a prominent communication and observation tower on Namsan Mountain that serves as one of Seoul’s most recognizable cityscape landmarks and tourist attractions.
  • C. Ok-dong
    Ok-dong is a neighborhood in Ulsan, South Korea, known for encompassing the large urban green space of Ulsan Grand Park.
  • D. Seongsan Ilchulbong
    Seongsan Ilchulbong is a dramatic tuff cone crater on the eastern coast of Jeju Island in South Korea, famed for its sunrise views and unique volcanic landscape.
  • E. Baegunsan
    Baegunsan is a mountain located in or near the city of Uiwang in South Korea, known for its hiking trails and natural scenery.
  • 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_69d381aaafc08190af475ef58dc16aba completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d2eefe8881908a672c4dca7657ca completed April 7, 2026, 9:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69d71d3f2c2c8190a71e4a896d8753e7 completed April 9, 2026, 3:30 a.m.
NEDg Description generation batch_69d7318402f08190b655bdddbd97ecb9 completed April 9, 2026, 4:56 a.m.
NED2 Entity disambiguation (via description) batch_69d734473ef48190852dbe48742a4273 completed April 9, 2026, 5:08 a.m.
Created at: April 6, 2026, 11:44 a.m.