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.