Triple

T728146
Position Surface form Disambiguated ID Type / Status
Subject Willis H. O’Brien E14772 entity
Predicate spouse P13 FINISHED
Object Darlene Pratt
Darlene Pratt was the wife of pioneering stop-motion animator and special effects artist Willis H. O’Brien.
E221720 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: Darlene Pratt | Statement: [Willis H. O’Brien, spouse, Darlene Pratt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Darlene Pratt
Context triple: [Willis H. O’Brien, spouse, Darlene Pratt]
  • A. Diane Monson
    Diane Monson is a California medical marijuana patient and activist who became a central figure in the U.S. Supreme Court case Gonzales v. Raich challenging federal authority over state-legal cannabis use.
  • B. Emily Drinkard
    Emily Drinkard, better known as Cissy Houston, is an American soul and gospel singer and the mother of Whitney Houston.
  • 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. Joanne Schieble
    Joanne Schieble is an American woman best known as the biological mother of Apple co-founder Steve Jobs.
  • E. Melinda Rogers
    Melinda Rogers is a Canadian business executive and member of the Rogers family, known for her leadership roles within Rogers Communications.
  • 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: Darlene Pratt
Triple: [Willis H. O’Brien, spouse, Darlene Pratt]
Generated description
Darlene Pratt was the wife of pioneering stop-motion animator and special effects artist Willis H. O’Brien.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Darlene Pratt
Target entity description: Darlene Pratt was the wife of pioneering stop-motion animator and special effects artist Willis H. O’Brien.
  • A. Diane Monson
    Diane Monson is a California medical marijuana patient and activist who became a central figure in the U.S. Supreme Court case Gonzales v. Raich challenging federal authority over state-legal cannabis use.
  • B. Emily Drinkard
    Emily Drinkard, better known as Cissy Houston, is an American soul and gospel singer and the mother of Whitney Houston.
  • 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. Joanne Schieble
    Joanne Schieble is an American woman best known as the biological mother of Apple co-founder Steve Jobs.
  • E. Melinda Rogers
    Melinda Rogers is a Canadian business executive and member of the Rogers family, known for her leadership roles within Rogers Communications.
  • 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_69a4934c753c81909b309027e48b9b3a completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a5c011948190b2cfccd8fe722742 completed March 1, 2026, 8:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69ae02eda1048190b5452b849315863f completed March 8, 2026, 11:14 p.m.
NEDg Description generation batch_69ae0386785c8190ae74e5f04a4809fc completed March 8, 2026, 11:17 p.m.
NED2 Entity disambiguation (via description) batch_69ae04253a80819092c112faddec1de1 completed March 8, 2026, 11:20 p.m.
Created at: March 1, 2026, 7:37 p.m.