Triple
T5311057
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mad Cows |
E119027
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object |
Sara Sugarman
Sara Sugarman is a Welsh film director, actress, and screenwriter known for her work on independent comedies and dramas.
|
E509901
|
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: Sara Sugarman | Statement: [Mad Cows, director, Sara Sugarman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sara Sugarman Context triple: [Mad Cows, director, Sara Sugarman]
-
A.
Gail Berman
Gail Berman is an American television and film producer and media executive known for her influential roles at major studios and for producing high-profile projects across network TV and Hollywood.
-
B.
Elaine Hyman
Elaine Hyman is known primarily as the spouse of Lloyd Wright, the American architect and son of Frank Lloyd Wright.
-
C.
Roberta Seidman
Roberta Seidman was the wife of American actor John Garfield, a prominent film star of the 1930s and 1940s.
-
D.
Sandy Stern
Sandy Stern is a film producer best known for his work on independent and cult-favorite movies, including the 1990 teen drama "Pump Up the Volume."
-
E.
Sari Gilman
Sari Gilman is a film editor best known for her work on the Academy Award–winning documentary "Taxi to the Dark Side."
- 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: Sara Sugarman Triple: [Mad Cows, director, Sara Sugarman]
Generated description
Sara Sugarman is a Welsh film director, actress, and screenwriter known for her work on independent comedies and dramas.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sara Sugarman Target entity description: Sara Sugarman is a Welsh film director, actress, and screenwriter known for her work on independent comedies and dramas.
-
A.
Gail Berman
Gail Berman is an American television and film producer and media executive known for her influential roles at major studios and for producing high-profile projects across network TV and Hollywood.
-
B.
Elaine Hyman
Elaine Hyman is known primarily as the spouse of Lloyd Wright, the American architect and son of Frank Lloyd Wright.
-
C.
Roberta Seidman
Roberta Seidman was the wife of American actor John Garfield, a prominent film star of the 1930s and 1940s.
-
D.
Sandy Stern
Sandy Stern is a film producer best known for his work on independent and cult-favorite movies, including the 1990 teen drama "Pump Up the Volume."
-
E.
Sari Gilman
Sari Gilman is a film editor best known for her work on the Academy Award–winning documentary "Taxi to the Dark Side."
- 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_69bd446b57bc8190a513d2e6c40314f3 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd85343ae08190bd9801ea4eac7003 |
completed | March 20, 2026, 5:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf11033c448190ab64600913ee8a9c |
completed | March 21, 2026, 9:43 p.m. |
| NEDg | Description generation | batch_69bf11c162f48190bdc56fea62575643 |
completed | March 21, 2026, 9:46 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69bf1237a644819081b1f1013e23cc66 |
completed | March 21, 2026, 9:48 p.m. |
Created at: March 20, 2026, 1:53 p.m.