Triple

T2399696
Position Surface form Disambiguated ID Type / Status
Subject Mary Lou Retton E47737 entity
Predicate familyName P18 FINISHED
Object Retton
Retton is the surname of Mary Lou Retton, the pioneering American gymnast who became an Olympic champion and national sports icon in the 1980s.
E263775 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: Retton | Statement: [Mary Lou Retton, familyName, Retton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Retton
Context triple: [Mary Lou Retton, familyName, Retton]
  • A. Dwan
    Dwan is the female lead character in the 1976 remake of King Kong, portrayed as the shipwrecked aspiring actress who forms a unique bond with the giant ape.
  • B. Everette
    Everette is the given first name of E. Howard Hunt, the American intelligence officer and author involved in the Watergate scandal.
  • C. Lamon
    Lamon is an archaeological site notable for inscriptions in the ancient Venetic language.
  • D. Rennie Wilford
    Rennie Wilford is the protagonist of Margaret Atwood’s novel "Bodily Harm," a travel journalist whose trip to a Caribbean island becomes a harrowing exploration of political unrest and personal vulnerability.
  • E. Heinsohn
    Heinsohn is a surname most prominently associated with Tom Heinsohn, a Hall of Fame Boston Celtics player, coach, and broadcaster.
  • 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: Retton
Triple: [Mary Lou Retton, familyName, Retton]
Generated description
Retton is the surname of Mary Lou Retton, the pioneering American gymnast who became an Olympic champion and national sports icon in the 1980s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Retton
Target entity description: Retton is the surname of Mary Lou Retton, the pioneering American gymnast who became an Olympic champion and national sports icon in the 1980s.
  • A. Dwan
    Dwan is the female lead character in the 1976 remake of King Kong, portrayed as the shipwrecked aspiring actress who forms a unique bond with the giant ape.
  • B. Everette
    Everette is the given first name of E. Howard Hunt, the American intelligence officer and author involved in the Watergate scandal.
  • C. Lamon
    Lamon is an archaeological site notable for inscriptions in the ancient Venetic language.
  • D. Rennie Wilford
    Rennie Wilford is the protagonist of Margaret Atwood’s novel "Bodily Harm," a travel journalist whose trip to a Caribbean island becomes a harrowing exploration of political unrest and personal vulnerability.
  • E. Heinsohn
    Heinsohn is a surname most prominently associated with Tom Heinsohn, a Hall of Fame Boston Celtics player, coach, and broadcaster.
  • 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_69a88a1c450c81909f61abb8b6863885 completed March 4, 2026, 7:38 p.m.
NER Named-entity recognition batch_69abc8c95d8c819088e4bb4fb32452ae completed March 7, 2026, 6:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69aeb3e081648190be42e9fc5046830f completed March 9, 2026, 11:49 a.m.
NEDg Description generation batch_69aeb4a5011c8190bda6c487dab73131 completed March 9, 2026, 11:53 a.m.
NED2 Entity disambiguation (via description) batch_69aeb59d0e5c819080bf5b34946b68ac completed March 9, 2026, 11:57 a.m.
Created at: March 4, 2026, 7:57 p.m.