Triple

T9928478
Position Surface form Disambiguated ID Type / Status
Subject Dong-gu, Busan E192582 entity
Predicate romanization P2508 FINISHED
Object Tong-gu
Tong-gu is the former romanized name for Dong-gu, a central district of Busan, South Korea.
E875119 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: Tong-gu | Statement: [Dong-gu, Busan, romanization, Tong-gu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tong-gu
Context triple: [Dong-gu, Busan, romanization, Tong-gu]
  • A. Geumwang-eup
    Geumwang-eup is a town-level administrative division in Eumseong County, located in North Chungcheong Province, South Korea.
  • B. Icheon
    Icheon is a South Korean city renowned for its traditional ceramics and hot spring resorts.
  • C. Sanchong District
    Sanchong District is a densely populated urban district in New Taipei City, Taiwan, situated across the river from central Taipei and known for its residential neighborhoods and commercial activity.
  • D. Sangil
    Sangil are an indigenous Moro ethnolinguistic group of the southern Philippines and nearby Indonesian islands, known for their seafaring traditions and Islamic faith.
  • E. Andong
    Andong is a historic city in South Korea renowned for its preserved traditional culture, including the Hahoe Folk Village and the Andong Mask Dance Festival.
  • 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: Tong-gu
Triple: [Dong-gu, Busan, romanization, Tong-gu]
Generated description
Tong-gu is the former romanized name for Dong-gu, a central district of Busan, South Korea.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tong-gu
Target entity description: Tong-gu is the former romanized name for Dong-gu, a central district of Busan, South Korea.
  • A. Geumwang-eup
    Geumwang-eup is a town-level administrative division in Eumseong County, located in North Chungcheong Province, South Korea.
  • B. Icheon
    Icheon is a South Korean city renowned for its traditional ceramics and hot spring resorts.
  • C. Sanchong District
    Sanchong District is a densely populated urban district in New Taipei City, Taiwan, situated across the river from central Taipei and known for its residential neighborhoods and commercial activity.
  • D. Sangil
    Sangil are an indigenous Moro ethnolinguistic group of the southern Philippines and nearby Indonesian islands, known for their seafaring traditions and Islamic faith.
  • E. Andong
    Andong is a historic city in South Korea renowned for its preserved traditional culture, including the Hahoe Folk Village and the Andong Mask Dance Festival.
  • 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_69ca82dd978c8190947124ab0d3315ac completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb59d7ad08190982a1584547190bd completed April 2, 2026, 12:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69d96af89e48819093a6c149ac988391 completed April 10, 2026, 9:26 p.m.
NEDg Description generation batch_69d96d85f9648190a43c8c924f5139e3 completed April 10, 2026, 9:37 p.m.
NED2 Entity disambiguation (via description) batch_69d96e1a36688190b97ced745bc6a30d completed April 10, 2026, 9:39 p.m.
Created at: March 30, 2026, 8:43 p.m.