Triple

T5775705
Position Surface form Disambiguated ID Type / Status
Subject George F. Will E127434 entity
Predicate spouse P13 FINISHED
Object Mari Maseng
Mari Maseng is an American political consultant and former White House communications director who has worked on multiple Republican campaigns and administrations.
 E542823 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: Mari Maseng | Statement: [George F. Will, spouse, Mari Maseng]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mari Maseng
Context triple: [George F. Will, spouse, Mari Maseng]
  • A. Maanami Mamani
    Maanami Mamani is a writer best known for contributing to the work "Through the Wire."
  • B. Maraita
    Maraita is a small municipality located in the Francisco Morazán Department of central Honduras.
  • C. Marape
    Marape is the surname of James Marape, the Prime Minister of Papua New Guinea.
  • D. Maganlal
    Maganlal is an Indian given name commonly used for men, particularly in Gujarati-speaking communities.
  • E. Marangona
    Marangona is the largest and most famous bell of St Mark's Campanile in Venice, traditionally used to mark the beginning and end of the working day and to signal important civic events.
  • 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: Mari Maseng
Triple: [George F. Will, spouse, Mari Maseng]
Generated description
Mari Maseng is an American political consultant and former White House communications director who has worked on multiple Republican campaigns and administrations.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mari Maseng
Target entity description: Mari Maseng is an American political consultant and former White House communications director who has worked on multiple Republican campaigns and administrations.
  • A. Maanami Mamani
    Maanami Mamani is a writer best known for contributing to the work "Through the Wire."
  • B. Maraita
    Maraita is a small municipality located in the Francisco Morazán Department of central Honduras.
  • C. Marape
    Marape is the surname of James Marape, the Prime Minister of Papua New Guinea.
  • D. Maganlal
    Maganlal is an Indian given name commonly used for men, particularly in Gujarati-speaking communities.
  • E. Marangona
    Marangona is the largest and most famous bell of St Mark's Campanile in Venice, traditionally used to mark the beginning and end of the working day and to signal important civic events.
  • 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_69c008361fa88190aefa4dc41b051e7f completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c029de3bb4819087a6f3e920e12990 completed March 22, 2026, 5:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69c07e6fd260819090d5e3c877c8bd31 completed March 22, 2026, 11:42 p.m.
NEDg Description generation batch_69c08ba48a1c819090f276116a084a01 completed March 23, 2026, 12:39 a.m.
NED2 Entity disambiguation (via description) batch_69c08c094bd08190bb3d849bf1a80ad0 completed March 23, 2026, 12:40 a.m.
Created at: March 22, 2026, 3:50 p.m.