Triple

T719851
Position Surface form Disambiguated ID Type / Status
Subject David Letterman E14391 entity
Predicate spouse P13 FINISHED
Object Regina Lasko
Regina Lasko is an American television production manager best known as the longtime partner and wife of late-night talk show host David Letterman.
E109583 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: Regina Lasko | Statement: [David Letterman, spouse, Regina Lasko]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Regina Lasko
Context triple: [David Letterman, spouse, Regina Lasko]
  • A. Rena Lalgie
    Rena Lalgie is a British civil servant who became the first Black woman to serve as Governor of Bermuda.
  • B. Karla Saaranen
    Karla Saaranen is a central, enigmatic love interest and morally complex figure in Gregory David Roberts' novel "Shantaram," deeply involved in the expatriate and criminal underworld of Bombay.
  • C. Cecilia Nessen
    Cecilia Nessen is a film producer best known for her work on the documentary "I Am Greta," which follows climate activist Greta Thunberg.
  • D. 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.
  • E. Lila Hotz
    Lila Hotz was the first wife of American magazine magnate Henry Luce, co-founder of Time Inc.
  • 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: Regina Lasko
Triple: [David Letterman, spouse, Regina Lasko]
Generated description
Regina Lasko is an American television production manager best known as the longtime partner and wife of late-night talk show host David Letterman.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Regina Lasko
Target entity description: Regina Lasko is an American television production manager best known as the longtime partner and wife of late-night talk show host David Letterman.
  • A. Rena Lalgie
    Rena Lalgie is a British civil servant who became the first Black woman to serve as Governor of Bermuda.
  • B. Karla Saaranen
    Karla Saaranen is a central, enigmatic love interest and morally complex figure in Gregory David Roberts' novel "Shantaram," deeply involved in the expatriate and criminal underworld of Bombay.
  • C. Cecilia Nessen
    Cecilia Nessen is a film producer best known for her work on the documentary "I Am Greta," which follows climate activist Greta Thunberg.
  • D. 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.
  • E. Lila Hotz
    Lila Hotz was the first wife of American magazine magnate Henry Luce, co-founder of Time Inc.
  • 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_69a7edf6b02c8190995c50a98b4ec326 completed March 4, 2026, 8:31 a.m.
NEDg Description generation batch_69a7f1cc03b48190a291ca9c20646648 completed March 4, 2026, 8:48 a.m.
NED2 Entity disambiguation (via description) batch_69a7f26264d48190ad04ee855523fcc1 completed March 4, 2026, 8:50 a.m.
Created at: March 1, 2026, 7:37 p.m.