Triple

T7604278
Position Surface form Disambiguated ID Type / Status
Subject Jang Kum-song E180060 entity
Predicate familyName P18 FINISHED
Object Jang
Jang is a Korean surname shared by numerous individuals across Korea and the Korean diaspora.
 E676140 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: Jang | Statement: [Jang Kum-song, familyName, Jang]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Jang
Context triple: [Jang Kum-song, familyName, Jang]
  • A. Jang
    Jang is one of the small islands that make up Maloelap Atoll in the Republic of the Marshall Islands.
  • B. Jin
    Jin is a Chinese surname historically associated with the Jewish community of Kaifeng, reflecting their integration into Chinese society while preserving distinct communal identities.
  • C. Jin
    Jin is the standard abbreviation used to refer to Shanxi Province in China.
  • D. Jeong
    Jeong is the Korean family name of Ken Jeong, the American comedian, actor, and physician known for roles in "The Hangover" series and the TV show "Community."
  • E. Jiyun
    Jiyun is an 11th-century Chinese rime dictionary that systematically records and organizes the phonology and characters of Middle Chinese.
  • 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: Jang
Triple: [Jang Kum-song, familyName, Jang]
Generated description
Jang is a Korean surname shared by numerous individuals across Korea and the Korean diaspora.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Jang
Target entity description: Jang is a Korean surname shared by numerous individuals across Korea and the Korean diaspora.
  • A. Jang
    Jang is one of the small islands that make up Maloelap Atoll in the Republic of the Marshall Islands.
  • B. Jin
    Jin is a Chinese surname historically associated with the Jewish community of Kaifeng, reflecting their integration into Chinese society while preserving distinct communal identities.
  • C. Jin
    Jin is the standard abbreviation used to refer to Shanxi Province in China.
  • D. Jeong
    Jeong is the Korean family name of Ken Jeong, the American comedian, actor, and physician known for roles in "The Hangover" series and the TV show "Community."
  • E. Jiyun
    Jiyun is an 11th-century Chinese rime dictionary that systematically records and organizes the phonology and characters of Middle Chinese.
  • 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_69c69f3567008190ab01d2ca7b53584a completed March 27, 2026, 3:16 p.m.
NER Named-entity recognition batch_69c6f9fbd1408190b721bf016f997c7b completed March 27, 2026, 9:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8684f3cf08190bc3cbafbd8c1b9a0 completed March 28, 2026, 11:46 p.m.
NEDg Description generation batch_69c86935488c8190854173b940a3e4bd completed March 28, 2026, 11:50 p.m.
NED2 Entity disambiguation (via description) batch_69c869b673c081908f2bb2eb59c2dec8 completed March 28, 2026, 11:52 p.m.
Created at: March 27, 2026, 3:54 p.m.