Triple

T13366883
Position Surface form Disambiguated ID Type / Status
Subject Kara Kennedy E318961 entity
Predicate spouse P13 FINISHED
Object Michael Allen
Michael Allen is an American lawyer best known as the husband of Kara Kennedy, the daughter of U.S. Senator Ted Kennedy.
E1037667 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: Michael Allen | Statement: [Kara Kennedy, spouse, Michael Allen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Allen
Context triple: [Kara Kennedy, spouse, Michael Allen]
  • A. Michael Kelso
    Michael Kelso is a dim-witted yet charming and good-looking teenager portrayed by Ashton Kutcher on the sitcom "That '70s Show."
  • B. Michael Henderson
    Michael Henderson is an author best known for writing the book "Window Seat."
  • C. Marvin Scandrick
    Marvin Scandrick, better known as Slim, is an American R&B singer and member of the group 112, recognized for his distinctive falsetto vocals and contributions to early-2000s R&B hits.
  • D. Allen Hoskins
    Allen Hoskins was an American child actor best known for his role as Farina in the early Our Gang (Little Rascals) comedy shorts.
  • E. John Sims
    John Sims is the protagonist of King Vidor’s 1928 silent film "The Crowd," representing the struggles and aspirations of an ordinary man in modern urban society.
  • 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: Michael Allen
Triple: [Kara Kennedy, spouse, Michael Allen]
Generated description
Michael Allen is an American lawyer best known as the husband of Kara Kennedy, the daughter of U.S. Senator Ted Kennedy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Michael Allen
Target entity description: Michael Allen is an American lawyer best known as the husband of Kara Kennedy, the daughter of U.S. Senator Ted Kennedy.
  • A. Michael Kelso
    Michael Kelso is a dim-witted yet charming and good-looking teenager portrayed by Ashton Kutcher on the sitcom "That '70s Show."
  • B. Michael Henderson
    Michael Henderson is an author best known for writing the book "Window Seat."
  • C. Marvin Scandrick
    Marvin Scandrick, better known as Slim, is an American R&B singer and member of the group 112, recognized for his distinctive falsetto vocals and contributions to early-2000s R&B hits.
  • D. Allen Hoskins
    Allen Hoskins was an American child actor best known for his role as Farina in the early Our Gang (Little Rascals) comedy shorts.
  • E. John Sims
    John Sims is the protagonist of King Vidor’s 1928 silent film "The Crowd," representing the struggles and aspirations of an ordinary man in modern urban society.
  • 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_69d806b7bbac8190b85278c87fa7aff3 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dadcd652d48190a782fd1f57f34b6a completed April 11, 2026, 11:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69f72680df088190b8dbcc8ad0d7366e completed May 3, 2026, 10:42 a.m.
NEDg Description generation batch_69f727512c94819091985c7942f40b31 completed May 3, 2026, 10:45 a.m.
NED2 Entity disambiguation (via description) batch_69f72b77d650819092c02f6488b2cfb2 completed May 3, 2026, 11:03 a.m.
Created at: April 9, 2026, 9:32 p.m.