Triple
T14191566
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sexy Beast |
E351724
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object |
Louis Mellis
Louis Mellis is a British screenwriter best known for co-writing the acclaimed crime film "Sexy Beast."
|
E1086558
|
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: Louis Mellis | Statement: [Sexy Beast, screenwriter, Louis Mellis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Louis Mellis Context triple: [Sexy Beast, screenwriter, Louis Mellis]
-
A.
Craig Bierko
Craig Bierko is an American actor known for his work in film, television, and theater, often playing charismatic or villainous roles.
-
B.
Lyor Boone
Lyor Boone is a fast-talking, socially awkward yet politically savvy White House political consultant featured in the TV series "Designated Survivor."
-
C.
Mike Kellin
Mike Kellin was an American character actor known for his prolific work in film, television, and theater from the 1950s through the 1970s.
-
D.
Marc Lacey
Marc Lacey is an American journalist and editor best known for serving in senior leadership roles at The New York Times, including overseeing major news coverage and editorial operations.
-
E.
Dan Baum
Dan Baum is an American entrepreneur best known as the founder of the online photo services company Shutterfly.
- 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: Louis Mellis Triple: [Sexy Beast, screenwriter, Louis Mellis]
Generated description
Louis Mellis is a British screenwriter best known for co-writing the acclaimed crime film "Sexy Beast."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Louis Mellis Target entity description: Louis Mellis is a British screenwriter best known for co-writing the acclaimed crime film "Sexy Beast."
-
A.
Craig Bierko
Craig Bierko is an American actor known for his work in film, television, and theater, often playing charismatic or villainous roles.
-
B.
Lyor Boone
Lyor Boone is a fast-talking, socially awkward yet politically savvy White House political consultant featured in the TV series "Designated Survivor."
-
C.
Mike Kellin
Mike Kellin was an American character actor known for his prolific work in film, television, and theater from the 1950s through the 1970s.
-
D.
Marc Lacey
Marc Lacey is an American journalist and editor best known for serving in senior leadership roles at The New York Times, including overseeing major news coverage and editorial operations.
-
E.
Dan Baum
Dan Baum is an American entrepreneur best known as the founder of the online photo services company Shutterfly.
- 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_69d827894ac0819097803e57f3227b23 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de61df628c8190ba3f557e2128dce5 |
completed | April 14, 2026, 3:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd1946eb68819096adf3c16a39818d |
completed | May 7, 2026, 10:59 p.m. |
| NEDg | Description generation | batch_69fd1eed1008819088635be43fbb1439 |
completed | May 7, 2026, 11:23 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69fd1f7c5d208190bab5d57e931fd082 |
completed | May 7, 2026, 11:25 p.m. |
Created at: April 10, 2026, 1:04 a.m.