Triple
T14080427
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lost Highway |
E338850
|
entity |
| Predicate | editor |
P1954
|
FINISHED |
| Object |
Mary Sweeney
Mary Sweeney is an American film editor, producer, and writer best known for her long-time collaboration with director David Lynch on projects such as "Lost Highway" and "Mulholland Drive."
|
E1178691
|
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: Mary Sweeney | Statement: [Lost Highway, editor, Mary Sweeney]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mary Sweeney Context triple: [Lost Highway, editor, Mary Sweeney]
-
A.
Maureen Sweeney
Maureen Sweeney is an Irish woman best known for her crucial World War II weather observations that influenced the timing of the D-Day landings.
-
B.
Ann Sweeny
Ann Sweeny is best known as the wife of acclaimed American television producer, director, and writer Gene Reynolds.
-
C.
Sarah O’Meara
Sarah O’Meara is known as the spouse of Australian film director Paul Cox.
-
D.
Lisa McGrillis
Lisa McGrillis is a British actress known for her work in television, film, and theatre, including roles in series like "Inspector George Gently" and "Mum."
-
E.
Mary Condon
Mary Condon is a Canadian legal scholar and academic leader who serves as the dean of Osgoode Hall Law School at York University.
- 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: Mary Sweeney Triple: [Lost Highway, editor, Mary Sweeney]
Generated description
Mary Sweeney is an American film editor, producer, and writer best known for her long-time collaboration with director David Lynch on projects such as "Lost Highway" and "Mulholland Drive."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mary Sweeney Target entity description: Mary Sweeney is an American film editor, producer, and writer best known for her long-time collaboration with director David Lynch on projects such as "Lost Highway" and "Mulholland Drive."
-
A.
Maureen Sweeney
Maureen Sweeney is an Irish woman best known for her crucial World War II weather observations that influenced the timing of the D-Day landings.
-
B.
Ann Sweeny
Ann Sweeny is best known as the wife of acclaimed American television producer, director, and writer Gene Reynolds.
-
C.
Sarah O’Meara
Sarah O’Meara is known as the spouse of Australian film director Paul Cox.
-
D.
Lisa McGrillis
Lisa McGrillis is a British actress known for her work in television, film, and theatre, including roles in series like "Inspector George Gently" and "Mum."
-
E.
Mary Condon
Mary Condon is a Canadian legal scholar and academic leader who serves as the dean of Osgoode Hall Law School at York University.
- 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_69d81c687b0c819087fd9ed4198403f8 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5c5f759c81909bfd60ab35b0937b |
completed | April 14, 2026, 3:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff99742618819083bba63ce9f27895 |
completed | May 9, 2026, 8:30 p.m. |
| NEDg | Description generation | batch_69ff9b3f6ef0819087ad4ffd2e85ec0e |
completed | May 9, 2026, 8:38 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ff9bebae208190a3a2f76ae9893238 |
completed | May 9, 2026, 8:41 p.m. |
Created at: April 9, 2026, 10:21 p.m.