Triple

T16870537
Position Surface form Disambiguated ID Type / Status
Subject Mark Yudof E421154 entity
Predicate familyName P18 FINISHED
Object Yudof
Yudof is the surname of Mark Yudof, an American law professor and former president of the University of California system.
 E1238431 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: Yudof | Statement: [Mark Yudof, familyName, Yudof]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Yudof
Context triple: [Mark Yudof, familyName, Yudof]
  • A. Yorii
    Yorii is a town in Saitama Prefecture, Japan, known as a regional residential and commuter hub connected to the greater Tokyo area.
  • B. Udaijin
    Udaijin was a high-ranking ministerial post in Japan’s historical imperial court, typically serving as one of the chief advisors and administrators directly beneath the top chancellor.
  • C. Yasu
    Yasu is a Japanese city located in Shiga Prefecture, known for its blend of residential areas, local industry, and proximity to Lake Biwa.
  • D. Ryogo
    Ryogo is a Japanese given name most notably borne by theoretical physicist Ryogo Kubo, known for his contributions to statistical mechanics and the fluctuation-dissipation theorem.
  • E. Yudi
    Yudi is the Jade Emperor, the supreme ruler of Heaven and chief deity in traditional Chinese folk religion and Taoism.
  • 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: Yudof
Triple: [Mark Yudof, familyName, Yudof]
Generated description
Yudof is the surname of Mark Yudof, an American law professor and former president of the University of California system.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Yudof
Target entity description: Yudof is the surname of Mark Yudof, an American law professor and former president of the University of California system.
  • A. Yorii
    Yorii is a town in Saitama Prefecture, Japan, known as a regional residential and commuter hub connected to the greater Tokyo area.
  • B. Udaijin
    Udaijin was a high-ranking ministerial post in Japan’s historical imperial court, typically serving as one of the chief advisors and administrators directly beneath the top chancellor.
  • C. Yasu
    Yasu is a Japanese city located in Shiga Prefecture, known for its blend of residential areas, local industry, and proximity to Lake Biwa.
  • D. Ryogo
    Ryogo is a Japanese given name most notably borne by theoretical physicist Ryogo Kubo, known for his contributions to statistical mechanics and the fluctuation-dissipation theorem.
  • E. Yudi
    Yudi is the Jade Emperor, the supreme ruler of Heaven and chief deity in traditional Chinese folk religion and Taoism.
  • 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_69d889d470fc8190b4aec199636c0c56 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e3b7f1fe5881909b18438d771814e9 completed April 18, 2026, 4:57 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00c2aeb9908190964a9403402186fb completed May 10, 2026, 5:38 p.m.
NEDg Description generation batch_6a00c3c25e9481908327bb6646212368 completed May 10, 2026, 5:43 p.m.
NED2 Entity disambiguation (via description) batch_6a00c44e37b48190a62b315ddbbd4ec4 completed May 10, 2026, 5:45 p.m.
Created at: April 10, 2026, 5:29 a.m.