Triple

T426836
Position Surface form Disambiguated ID Type / Status
Subject Larry King E9626 entity
Predicate spouse P13 FINISHED
Object Shawn Southwick
Shawn Southwick is an American singer, actress, and television host best known for her long-term marriage to broadcaster Larry King.
 E90767 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: Shawn Southwick | Statement: [Larry King, spouse, Shawn Southwick]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Shawn Southwick
Context triple: [Larry King, spouse, Shawn Southwick]
  • A. Paul Merolla
    Paul Merolla is a neuroscientist and engineer best known as a co-founder of Neuralink, the neurotechnology company developing brain–computer interfaces.
  • B. Andrew Dunn
    Andrew Dunn is a British cinematographer known for his work on numerous high-profile films and television productions.
  • C. Michael H. Moloney
    Michael H. Moloney is a physics-focused science policy and leadership professional who serves as the chief executive officer of the American Institute of Physics.
  • D. Mark Daboll
    Mark Daboll is a member of the Daboll family, related to NFL head coach Brian Daboll.
  • E. Michael Rogers
    Michael Rogers is a relatively common personal name shared by multiple individuals across fields such as politics, sports, and the arts, rather than referring to one singular widely recognized figure.
  • 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: Shawn Southwick
Triple: [Larry King, spouse, Shawn Southwick]
Generated description
Shawn Southwick is an American singer, actress, and television host best known for her long-term marriage to broadcaster Larry King.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Shawn Southwick
Target entity description: Shawn Southwick is an American singer, actress, and television host best known for her long-term marriage to broadcaster Larry King.
  • A. Paul Merolla
    Paul Merolla is a neuroscientist and engineer best known as a co-founder of Neuralink, the neurotechnology company developing brain–computer interfaces.
  • B. Andrew Dunn
    Andrew Dunn is a British cinematographer known for his work on numerous high-profile films and television productions.
  • C. Michael H. Moloney
    Michael H. Moloney is a physics-focused science policy and leadership professional who serves as the chief executive officer of the American Institute of Physics.
  • D. Mark Daboll
    Mark Daboll is a member of the Daboll family, related to NFL head coach Brian Daboll.
  • E. Michael Rogers
    Michael Rogers is a relatively common personal name shared by multiple individuals across fields such as politics, sports, and the arts, rather than referring to one singular widely recognized figure.
  • 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_69a2e801e1d48190b505d1dd336b52ac completed Feb. 28, 2026, 1:05 p.m.
NER Named-entity recognition batch_69a2eed691c4819092b7e57306114bbc completed Feb. 28, 2026, 1:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69a66660d36481909b938cf569337df9 completed March 3, 2026, 4:41 a.m.
NEDg Description generation batch_69a666f5d80481908363e622337db227 completed March 3, 2026, 4:43 a.m.
NED2 Entity disambiguation (via description) batch_69a66748ce7c81908d1cbc6e8767a368 completed March 3, 2026, 4:44 a.m.
Created at: Feb. 28, 2026, 1:11 p.m.