Triple

T4705687
Position Surface form Disambiguated ID Type / Status
Subject Do Ho Suh E104386 entity
Predicate familyName P18 FINISHED
Object Suh
Suh is a Korean surname shared by various notable figures in fields such as art, politics, and academia.
 E463676 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: Suh | Statement: [Do Ho Suh, familyName, Suh]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Suh
Context triple: [Do Ho Suh, familyName, Suh]
  • A. Sunam
    Sunam is a town in the Sangrur district of Punjab, India, known as the birthplace of Indian revolutionary Udham Singh.
  • B. Suinula
    Suinula is a locality in Finland historically noted as a site of significant events during the Finnish Civil War’s White Terror period.
  • C. Sutan
    Sutan is the given name of Sutan Sjahrir, an influential Indonesian nationalist leader and the country’s first prime minister.
  • D. Syukuro
    Syukuro is the given name of Syukuro Manabe, a pioneering climatologist known for his foundational work on climate modeling and global warming.
  • E. Yahi
    The Yahi were a small Native American group from northern California, known for being among the last surviving independent Indigenous peoples in the region and for the story of Ishi, their last known member.
  • 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: Suh
Triple: [Do Ho Suh, familyName, Suh]
Generated description
Suh is a Korean surname shared by various notable figures in fields such as art, politics, and academia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Suh
Target entity description: Suh is a Korean surname shared by various notable figures in fields such as art, politics, and academia.
  • A. Sunam
    Sunam is a town in the Sangrur district of Punjab, India, known as the birthplace of Indian revolutionary Udham Singh.
  • B. Suinula
    Suinula is a locality in Finland historically noted as a site of significant events during the Finnish Civil War’s White Terror period.
  • C. Sutan
    Sutan is the given name of Sutan Sjahrir, an influential Indonesian nationalist leader and the country’s first prime minister.
  • D. Syukuro
    Syukuro is the given name of Syukuro Manabe, a pioneering climatologist known for his foundational work on climate modeling and global warming.
  • E. Yahi
    The Yahi were a small Native American group from northern California, known for being among the last surviving independent Indigenous peoples in the region and for the story of Ishi, their last known member.
  • 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_69bd43eac3c08190af7e4020c6c3704c completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd63e808c88190877e98408498fb62 completed March 20, 2026, 3:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69be1067c6a081909fa06689ea66a8a4 completed March 21, 2026, 3:28 a.m.
NEDg Description generation batch_69be133c5a8c8190b3c0f066c4ab44a9 completed March 21, 2026, 3:40 a.m.
NED2 Entity disambiguation (via description) batch_69be13cafd1c8190aec0efe6328c25b8 completed March 21, 2026, 3:43 a.m.
Created at: March 20, 2026, 1:17 p.m.