Triple

T4048064
Position Surface form Disambiguated ID Type / Status
Subject Karen Pence E84115 entity
Predicate birthName P65 FINISHED
Object Karen Sue Batten
Karen Sue Batten, better known as Karen Pence, is an American schoolteacher, watercolor artist, and former Second Lady of the United States as the wife of former Vice President Mike Pence.
 E432631 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: Karen Sue Batten | Statement: [Karen Pence, birthName, Karen Sue Batten]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Karen Sue Batten
Context triple: [Karen Pence, birthName, Karen Sue Batten]
  • A. Laura Ricketts
    Laura Ricketts is an American attorney, co-owner of the Chicago Cubs, and prominent LGBTQ+ activist and political donor.
  • B. Karen Gunderson
    Karen Gunderson is an American singer best known as a member of the folk music group The New Christy Minstrels.
  • C. Cheryl Alley
    Cheryl Alley, also known as Cheryl Howard, is an American writer and actress best known as the longtime wife of filmmaker Ron Howard.
  • D. Emily Drinkard
    Emily Drinkard, better known as Cissy Houston, is an American soul and gospel singer and the mother of Whitney Houston.
  • E. Colleen Ahland
    Colleen Ahland is a linguist known for her research on the Koman languages of Ethiopia and Sudan, focusing on their documentation, description, and classification.
  • 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: Karen Sue Batten
Triple: [Karen Pence, birthName, Karen Sue Batten]
Generated description
Karen Sue Batten, better known as Karen Pence, is an American schoolteacher, watercolor artist, and former Second Lady of the United States as the wife of former Vice President Mike Pence.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Karen Sue Batten
Target entity description: Karen Sue Batten, better known as Karen Pence, is an American schoolteacher, watercolor artist, and former Second Lady of the United States as the wife of former Vice President Mike Pence.
  • A. Laura Ricketts
    Laura Ricketts is an American attorney, co-owner of the Chicago Cubs, and prominent LGBTQ+ activist and political donor.
  • B. Karen Gunderson
    Karen Gunderson is an American singer best known as a member of the folk music group The New Christy Minstrels.
  • C. Cheryl Alley
    Cheryl Alley, also known as Cheryl Howard, is an American writer and actress best known as the longtime wife of filmmaker Ron Howard.
  • D. Emily Drinkard
    Emily Drinkard, better known as Cissy Houston, is an American soul and gospel singer and the mother of Whitney Houston.
  • E. Colleen Ahland
    Colleen Ahland is a linguist known for her research on the Koman languages of Ethiopia and Sudan, focusing on their documentation, description, and classification.
  • 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_69aed930bd5c819083e7dcc14fc44f69 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefb81040481909b22e4c445ecae0f completed March 9, 2026, 4:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5db6b01e48190a2e02597347f3348 completed March 14, 2026, 10:04 p.m.
NEDg Description generation batch_69b5dc578b08819095cbf6ba8470d3e0 completed March 14, 2026, 10:08 p.m.
NED2 Entity disambiguation (via description) batch_69b5dd1b03508190a47bb6fb93f22ad8 completed March 14, 2026, 10:11 p.m.
Created at: March 9, 2026, 3:37 p.m.