Triple
T14657115
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clean and Sober |
E344139
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object |
Tod Carroll
Tod Carroll is an American screenwriter best known for his work on the 1988 drama film "Clean and Sober."
|
E1112992
|
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: Tod Carroll | Statement: [Clean and Sober, screenwriter, Tod Carroll]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tod Carroll Context triple: [Clean and Sober, screenwriter, Tod Carroll]
-
A.
Matt Carroll
Matt Carroll is an Australian film producer best known for his work on acclaimed films such as "Breaker Morant."
-
B.
Kent Carroll
Kent Carroll is a publisher best known as the co-founder of the independent publishing house Carroll & Graf.
-
C.
Luke Carroll
Luke Carroll is a film producer best known for his work on the animated science-fiction comedy "Escape from Planet Earth."
-
D.
Kevin Carroll
Kevin Carroll is an American actor known for his work in film and television, including a role in the Netflix miniseries "Self Made: Inspired by the Life of Madam C. J. Walker."
-
E.
Sean Carson
Sean Carson is a central character in the drama film "Pieces of a Woman," portrayed as the grieving partner struggling to cope with the aftermath of a tragic home birth.
- 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: Tod Carroll Triple: [Clean and Sober, screenwriter, Tod Carroll]
Generated description
Tod Carroll is an American screenwriter best known for his work on the 1988 drama film "Clean and Sober."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tod Carroll Target entity description: Tod Carroll is an American screenwriter best known for his work on the 1988 drama film "Clean and Sober."
-
A.
Matt Carroll
Matt Carroll is an Australian film producer best known for his work on acclaimed films such as "Breaker Morant."
-
B.
Kent Carroll
Kent Carroll is a publisher best known as the co-founder of the independent publishing house Carroll & Graf.
-
C.
Luke Carroll
Luke Carroll is a film producer best known for his work on the animated science-fiction comedy "Escape from Planet Earth."
-
D.
Kevin Carroll
Kevin Carroll is an American actor known for his work in film and television, including a role in the Netflix miniseries "Self Made: Inspired by the Life of Madam C. J. Walker."
-
E.
Sean Carson
Sean Carson is a central character in the drama film "Pieces of a Woman," portrayed as the grieving partner struggling to cope with the aftermath of a tragic home birth.
- 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_69d822e1a2cc81908e5bb93cf61ce3cc |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb51a562c819098971447db4b29f7 |
completed | April 14, 2026, 9:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fdd5de0b98819094c32765e4cb3f9c |
completed | May 8, 2026, 12:23 p.m. |
| NEDg | Description generation | batch_69fddd8d7da481909d38d9390770939c |
completed | May 8, 2026, 12:56 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69fdde23da708190b7eabeed6a9cb169 |
completed | May 8, 2026, 12:59 p.m. |
Created at: April 10, 2026, 1:27 a.m.