Triple

T1763320
Position Surface form Disambiguated ID Type / Status
Subject Laura Dern E38705 entity
Predicate characterPortrayed P1507 FINISHED
Object Sandy Williams
Sandy Williams is the naive yet courageous small-town college student Laura Dern portrays in David Lynch’s neo-noir film "Blue Velvet."
E219956 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: Sandy Williams | Statement: [Laura Dern, characterPortrayed, Sandy Williams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sandy Williams
Context triple: [Laura Dern, characterPortrayed, Sandy Williams]
  • A. Dominique McElligott
    Dominique McElligott is an Irish actress known for her roles in television series such as Hell on Wheels, House of Cards, and The Boys.
  • B. Dawn Laurel-Jones
    Dawn Laurel-Jones is a photographer and the wife of American actor and filmmaker Tommy Lee Jones.
  • C. Vondie Curtis-Hall
    Vondie Curtis-Hall is an American actor and filmmaker known for his work in film and television, both in front of and behind the camera.
  • D. Cynthia Wesley
    Cynthia Wesley was one of the four African-American girls killed in the 1963 bombing of the 16th Street Baptist Church in Birmingham, Alabama, a pivotal tragedy of the Civil Rights Movement.
  • E. Ruby Aldridge
    Ruby Aldridge is an American fashion model known for her runway and editorial work with major designers and magazines.
  • 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: Sandy Williams
Triple: [Laura Dern, characterPortrayed, Sandy Williams]
Generated description
Sandy Williams is the naive yet courageous small-town college student Laura Dern portrays in David Lynch’s neo-noir film "Blue Velvet."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sandy Williams
Target entity description: Sandy Williams is the naive yet courageous small-town college student Laura Dern portrays in David Lynch’s neo-noir film "Blue Velvet."
  • A. Dominique McElligott
    Dominique McElligott is an Irish actress known for her roles in television series such as Hell on Wheels, House of Cards, and The Boys.
  • B. Dawn Laurel-Jones
    Dawn Laurel-Jones is a photographer and the wife of American actor and filmmaker Tommy Lee Jones.
  • C. Vondie Curtis-Hall
    Vondie Curtis-Hall is an American actor and filmmaker known for his work in film and television, both in front of and behind the camera.
  • D. Cynthia Wesley
    Cynthia Wesley was one of the four African-American girls killed in the 1963 bombing of the 16th Street Baptist Church in Birmingham, Alabama, a pivotal tragedy of the Civil Rights Movement.
  • E. Ruby Aldridge
    Ruby Aldridge is an American fashion model known for her runway and editorial work with major designers and magazines.
  • 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_69a8862d562481908d7025a1c1f67c0d completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa6465245c8190b1ee84628c62c529 completed March 6, 2026, 5:21 a.m.
NED1 Entity disambiguation (via context triple) batch_69adfb98fee88190804f368b484c7305 completed March 8, 2026, 10:43 p.m.
NEDg Description generation batch_69adfc81697c8190b0dd847649f28923 completed March 8, 2026, 10:47 p.m.
NED2 Entity disambiguation (via description) batch_69adfdc8a7f481909b2ee0b4444cf4b9 completed March 8, 2026, 10:52 p.m.
Created at: March 4, 2026, 7:31 p.m.