Triple

T719852
Position Surface form Disambiguated ID Type / Status
Subject David Letterman E14391 entity
Predicate spouse P13 FINISHED
Object Michelle Cook
Michelle Cook is an American woman best known as the first wife of television host and comedian David Letterman.
E214923 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: Michelle Cook | Statement: [David Letterman, spouse, Michelle Cook]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michelle Cook
Context triple: [David Letterman, spouse, Michelle Cook]
  • A. Colleen Sostorics
    Colleen Sostorics is a Canadian former ice hockey defenceman and three-time Olympic gold medallist who starred with the national women’s team.
  • B. Carolyn Hockett
    Carolyn Hockett is known for being one of the later wives of American actor and entertainer Mickey Rooney.
  • C. Pamela Tatge
    Pamela Tatge is an American arts leader and curator known for directing major performing arts institutions, including serving as artistic director of the renowned dance center and festival Jacob’s Pillow.
  • D. Caryn Elaine Johnson
    Caryn Elaine Johnson is the birth name of Whoopi Goldberg, the acclaimed American actress, comedian, and television host.
  • E. Emily Drinkard
    Emily Drinkard, better known as Cissy Houston, is an American soul and gospel singer and the mother of Whitney Houston.
  • 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: Michelle Cook
Triple: [David Letterman, spouse, Michelle Cook]
Generated description
Michelle Cook is an American woman best known as the first wife of television host and comedian David Letterman.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Michelle Cook
Target entity description: Michelle Cook is an American woman best known as the first wife of television host and comedian David Letterman.
  • A. Colleen Sostorics
    Colleen Sostorics is a Canadian former ice hockey defenceman and three-time Olympic gold medallist who starred with the national women’s team.
  • B. Carolyn Hockett
    Carolyn Hockett is known for being one of the later wives of American actor and entertainer Mickey Rooney.
  • C. Pamela Tatge
    Pamela Tatge is an American arts leader and curator known for directing major performing arts institutions, including serving as artistic director of the renowned dance center and festival Jacob’s Pillow.
  • D. Caryn Elaine Johnson
    Caryn Elaine Johnson is the birth name of Whoopi Goldberg, the acclaimed American actress, comedian, and television host.
  • E. Emily Drinkard
    Emily Drinkard, better known as Cissy Houston, is an American soul and gospel singer and the mother of Whitney Houston.
  • 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_69a4934a36e081909e7abef98b898a4e completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a58e65e8819098cba7e6a20d8f33 completed March 1, 2026, 8:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69adf39f5694819086fcdbd27fa2ea4b completed March 8, 2026, 10:09 p.m.
NEDg Description generation batch_69adf471909881909de20d9d1fa0b372 completed March 8, 2026, 10:13 p.m.
NED2 Entity disambiguation (via description) batch_69adf50b17a081909b93ad3e08c71772 completed March 8, 2026, 10:15 p.m.
Created at: March 1, 2026, 7:37 p.m.