Triple

T4560119
Position Surface form Disambiguated ID Type / Status
Subject Drop Dead Gorgeous E120571 entity
Predicate screenwriter P2831 FINISHED
Object Lona Williams
Lona Williams is an American screenwriter and producer best known for writing the dark comedy film "Drop Dead Gorgeous."
E453375 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: Lona Williams | Statement: [Drop Dead Gorgeous, screenwriter, Lona Williams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lona Williams
Context triple: [Drop Dead Gorgeous, screenwriter, Lona Williams]
  • A. Ramona Isabel Wright
    Ramona Isabel Wright is the daughter of Tré Cool, the drummer of the American punk rock band Green Day.
  • B. Zora Folley
    Zora Folley was an American heavyweight boxer of the 1950s and 1960s, best known for challenging Muhammad Ali for the world title in 1967.
  • C. Leola Brown
    Leola Brown was the wife of Oliver Brown, the named plaintiff in the landmark U.S. Supreme Court school desegregation case Brown v. Board of Education.
  • D. Leontine Drinkard
    Leontine Drinkard was a member of the prominent Warwick–Houston musical family, known as the matriarchal lineage behind singers like Cissy Houston and Whitney Houston.
  • E. Lillian Jean Williams
    Lillian Jean Williams was the lyricist who wrote the words to Nigeria’s former national anthem, “Nigeria, We Hail Thee.”
  • 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: Lona Williams
Triple: [Drop Dead Gorgeous, screenwriter, Lona Williams]
Generated description
Lona Williams is an American screenwriter and producer best known for writing the dark comedy film "Drop Dead Gorgeous."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lona Williams
Target entity description: Lona Williams is an American screenwriter and producer best known for writing the dark comedy film "Drop Dead Gorgeous."
  • A. Ramona Isabel Wright
    Ramona Isabel Wright is the daughter of Tré Cool, the drummer of the American punk rock band Green Day.
  • B. Zora Folley
    Zora Folley was an American heavyweight boxer of the 1950s and 1960s, best known for challenging Muhammad Ali for the world title in 1967.
  • C. Leola Brown
    Leola Brown was the wife of Oliver Brown, the named plaintiff in the landmark U.S. Supreme Court school desegregation case Brown v. Board of Education.
  • D. Leontine Drinkard
    Leontine Drinkard was a member of the prominent Warwick–Houston musical family, known as the matriarchal lineage behind singers like Cissy Houston and Whitney Houston.
  • E. Lillian Jean Williams
    Lillian Jean Williams was the lyricist who wrote the words to Nigeria’s former national anthem, “Nigeria, We Hail Thee.”
  • 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_69bd4636f1648190a701445c2fcd9c17 completed March 20, 2026, 1:05 p.m.
NER Named-entity recognition batch_69bd582b871c8190be0b70c76d639000 completed March 20, 2026, 2:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdd3aa3b9081908984777207f4040e completed March 20, 2026, 11:09 p.m.
NEDg Description generation batch_69bdd4b703748190a17cf4f02456c39a completed March 20, 2026, 11:13 p.m.
NED2 Entity disambiguation (via description) batch_69bdd548ea348190818f4335b8ebad2e completed March 20, 2026, 11:16 p.m.
Created at: March 20, 2026, 1:09 p.m.