Triple

T1024583
Position Surface form Disambiguated ID Type / Status
Subject Mike Pence E22110 entity
Predicate spouse P13 FINISHED
Object Karen Pence E84115 NE FINISHED

How this triple was built (2 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 Pence | Statement: [Mike Pence, spouse, Karen Pence]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karen Pence
Context triple: [Mike Pence, spouse, Karen Pence]
  • A. Karen Pence chosen
    Karen Pence is an American educator and watercolor artist who served as Second Lady of the United States during Mike Pence’s vice presidency.
  • B. Bill Pence
    Bill Pence was an American film executive and co-founder of the influential Telluride Film Festival, known for shaping the landscape of international film exhibition and appreciation.
  • C. Mike Pence
    Mike Pence is an American politician who served as the 48th vice president of the United States and former governor of Indiana.
  • D. Ivanka Trump
    Ivanka Trump is an American businesswoman, former fashion model, and political advisor who served as a senior advisor to her father, President Donald Trump, during his administration.
  • E. Kathy Kraninger
    Kathy Kraninger is an American government official who served as Director of the Consumer Financial Protection Bureau under the Trump administration.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a493d6e380819097b384986ffc315c completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b7e28df08190b5be7794442a6f21 completed March 1, 2026, 10:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac4c12604c8190b3ce04c96b0000f1 completed March 7, 2026, 4:02 p.m.
Created at: March 1, 2026, 7:41 p.m.