Triple
T10681243
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Look Who’s Talking |
E251759
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object |
James Ubriacco
James Ubriacco is a charming New York cab driver who becomes a devoted father figure and romantic partner in the comedic film series "Look Who’s Talking."
|
E878857
|
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: James Ubriacco | Statement: [Look Who’s Talking, mainCharacter, James Ubriacco]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: James Ubriacco Context triple: [Look Who’s Talking, mainCharacter, James Ubriacco]
-
A.
Jeffrey Levy-Hinte
Jeffrey Levy-Hinte is an American film producer known for his work on acclaimed independent films such as "The Kids Are All Right" and "Thirteen."
-
B.
Jonathan Littman
Jonathan Littman is a television producer best known for his executive production work on the CSI franchise and other major crime and drama series.
-
C.
Brian Raffel
Brian Raffel is an American video game developer and co-founder of Raven Software, known for his leadership on titles such as the Heretic and Hexen series.
-
D.
Jeffrey Auerbach
Jeffrey Auerbach is a film producer best known for his work on the stop-motion animated feature "Corpse Bride."
-
E.
Matthew Salsberg
Matthew Salsberg is a television writer and producer best known for his work on the dark comedy series "Weeds."
- 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: James Ubriacco Triple: [Look Who’s Talking, mainCharacter, James Ubriacco]
Generated description
James Ubriacco is a charming New York cab driver who becomes a devoted father figure and romantic partner in the comedic film series "Look Who’s Talking."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: James Ubriacco Target entity description: James Ubriacco is a charming New York cab driver who becomes a devoted father figure and romantic partner in the comedic film series "Look Who’s Talking."
-
A.
Jeffrey Levy-Hinte
Jeffrey Levy-Hinte is an American film producer known for his work on acclaimed independent films such as "The Kids Are All Right" and "Thirteen."
-
B.
Jonathan Littman
Jonathan Littman is a television producer best known for his executive production work on the CSI franchise and other major crime and drama series.
-
C.
Brian Raffel
Brian Raffel is an American video game developer and co-founder of Raven Software, known for his leadership on titles such as the Heretic and Hexen series.
-
D.
Jeffrey Auerbach
Jeffrey Auerbach is a film producer best known for his work on the stop-motion animated feature "Corpse Bride."
-
E.
Matthew Salsberg
Matthew Salsberg is a television writer and producer best known for his work on the dark comedy series "Weeds."
- 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_69d6aa5bd7c08190a816e733b4045c23 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6fcc1b8d4819082fde22db39d8b24 |
completed | April 9, 2026, 1:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d98885abf88190b54ed9db779d3ff0 |
completed | April 10, 2026, 11:32 p.m. |
| NEDg | Description generation | batch_69d98aea391c81909ec64a29053c35c1 |
completed | April 10, 2026, 11:42 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d98c013348819094bde38a057257b4 |
completed | April 10, 2026, 11:47 p.m. |
Created at: April 8, 2026, 9:10 p.m.