Triple

T395703
Position Surface form Disambiguated ID Type / Status
Subject Norman Rockwell E8977 entity
Predicate spouse P13 FINISHED
Object Molly Punderson
Molly Punderson was the wife of American illustrator Norman Rockwell and a figure in his early personal life and career.
E156771 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: Molly Punderson | Statement: [Norman Rockwell, spouse, Molly Punderson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Molly Punderson
Context triple: [Norman Rockwell, spouse, Molly Punderson]
  • A. Erin McDermott
    Erin McDermott is a collegiate sports administrator best known as the athletic director at Harvard University.
  • B. Janel Moloney
    Janel Moloney is an American actress best known for her role as Donna Moss on the political drama television series "The West Wing."
  • C. Natalie Schafer
    Natalie Schafer was an American actress best known for playing the wealthy and daffy Lovey Howell on the classic television sitcom "Gilligan's Island."
  • D. Anna Beth Sully
    Anna Beth Sully was the first wife of silent film star Douglas Fairbanks, whom she married before his rise to Hollywood fame.
  • E. Kristen Tomassi
    Kristen Tomassi is an American architect and designer best known as the first wife of British entrepreneur Richard Branson.
  • 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: Molly Punderson
Triple: [Norman Rockwell, spouse, Molly Punderson]
Generated description
Molly Punderson was the wife of American illustrator Norman Rockwell and a figure in his early personal life and career.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Molly Punderson
Target entity description: Molly Punderson was the wife of American illustrator Norman Rockwell and a figure in his early personal life and career.
  • A. Erin McDermott
    Erin McDermott is a collegiate sports administrator best known as the athletic director at Harvard University.
  • B. Janel Moloney
    Janel Moloney is an American actress best known for her role as Donna Moss on the political drama television series "The West Wing."
  • C. Natalie Schafer
    Natalie Schafer was an American actress best known for playing the wealthy and daffy Lovey Howell on the classic television sitcom "Gilligan's Island."
  • D. Anna Beth Sully
    Anna Beth Sully was the first wife of silent film star Douglas Fairbanks, whom she married before his rise to Hollywood fame.
  • E. Kristen Tomassi
    Kristen Tomassi is an American architect and designer best known as the first wife of British entrepreneur Richard Branson.
  • 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_69a2e7f55c60819097aff65ea2ca2832 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ec792dd081909b6b18a854139f8c completed Feb. 28, 2026, 1:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69acce4b94d08190b7747b0b6d61e3e1 completed March 8, 2026, 1:18 a.m.
NEDg Description generation batch_69accf3931bc81908e38755e2d024270 completed March 8, 2026, 1:22 a.m.
NED2 Entity disambiguation (via description) batch_69accfb8acfc8190bba379d8bb114c29 completed March 8, 2026, 1:24 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.