Triple
T12278818
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taxi |
E292660
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object |
Tony Banta
Tony Banta is a kind-hearted but somewhat dim-witted boxer and cab driver portrayed by Tony Danza on the classic sitcom "Taxi."
|
E975914
|
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: Tony Banta | Statement: [Taxi, mainCharacter, Tony Banta]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tony Banta Context triple: [Taxi, mainCharacter, Tony Banta]
-
A.
Gary Bonner
Gary Bonner is a musician best known as a member of the new wave band Tom Tom Club.
-
B.
Gary Tarpinian
Gary Tarpinian was an American television producer best known for creating and producing popular nonfiction and reality series, particularly in the history and science genres.
-
C.
Verne Brown
Verne Brown is one of the time-traveling sons of Dr. Emmett Brown featured in the Back to the Future franchise.
-
D.
Matt Bondurant
Matt Bondurant is an American novelist and academic best known for his historical crime novel "The Wettest County in the World," which was adapted into the film "Lawless."
-
E.
Ted Daughety
Ted Daughety is an American physician and pulmonologist best known as the husband of Kansas Governor Laura Kelly.
- 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: Tony Banta Triple: [Taxi, mainCharacter, Tony Banta]
Generated description
Tony Banta is a kind-hearted but somewhat dim-witted boxer and cab driver portrayed by Tony Danza on the classic sitcom "Taxi."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tony Banta Target entity description: Tony Banta is a kind-hearted but somewhat dim-witted boxer and cab driver portrayed by Tony Danza on the classic sitcom "Taxi."
-
A.
Gary Bonner
Gary Bonner is a musician best known as a member of the new wave band Tom Tom Club.
-
B.
Gary Tarpinian
Gary Tarpinian was an American television producer best known for creating and producing popular nonfiction and reality series, particularly in the history and science genres.
-
C.
Verne Brown
Verne Brown is one of the time-traveling sons of Dr. Emmett Brown featured in the Back to the Future franchise.
-
D.
Matt Bondurant
Matt Bondurant is an American novelist and academic best known for his historical crime novel "The Wettest County in the World," which was adapted into the film "Lawless."
-
E.
Ted Daughety
Ted Daughety is an American physician and pulmonologist best known as the husband of Kansas Governor Laura Kelly.
- 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_69d6ab6856488190b5d31178d5015f8e |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d91cf1ab8c8190a51f498bfda957d8 |
completed | April 10, 2026, 3:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f61e6f46f08190839ba07ef6fac984 |
completed | May 2, 2026, 3:55 p.m. |
| NEDg | Description generation | batch_69f622de74f0819096c5f5bf6f938fe7 |
completed | May 2, 2026, 4:14 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f62379746c8190bc9da48775b86dfa |
completed | May 2, 2026, 4:16 p.m. |
Created at: April 8, 2026, 9:52 p.m.