Triple
T12700077
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Scandal |
E303436
|
entity |
| Predicate | hasCastMember |
P2308
|
FINISHED |
| Object |
Columbus Short
Columbus Short is an American actor and choreographer best known for his role as Harrison Wright on the television drama series "Scandal."
|
E467295
|
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: Columbus Short | Statement: [Scandal, hasCastMember, Columbus Short]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Columbus Short Context triple: [Scandal, hasCastMember, Columbus Short]
-
A.
Tin Lizzie
Tin Lizzie is the popular nickname for the Ford Model T, the early 20th-century automobile that revolutionized mass car production and personal transportation.
-
B.
Shibe
Shibe is a surname most notably associated with Ben Shibe, an early 20th-century American baseball executive and co-owner of the Philadelphia Athletics.
-
C.
Skokie Swift
Skokie Swift is the former name of the Chicago Transit Authority’s Yellow Line rapid transit service connecting Chicago with the suburb of Skokie.
-
D.
The Allen
The Allen is the commonly used local name for Allen Road, a major expressway in Toronto, Ontario, Canada.
-
E.
Pacer
Pacer is the horse-themed mascot representing the University of South Carolina Aiken’s athletic teams.
- 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: Columbus Short Triple: [Scandal, hasCastMember, Columbus Short]
Generated description
Columbus Short is an American actor and choreographer best known for his role as Harrison Wright on the television drama series "Scandal."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Columbus Short Target entity description: Columbus Short is an American actor and choreographer best known for his role as Harrison Wright on the television drama series "Scandal."
-
A.
Columbus Short
chosen
Columbus Short is an American actor and choreographer best known for roles in films like "Stomp the Yard" and the TV series "Scandal."
-
B.
Tin Lizzie
Tin Lizzie is the popular nickname for the Ford Model T, the early 20th-century automobile that revolutionized mass car production and personal transportation.
-
C.
Shibe
Shibe is a surname most notably associated with Ben Shibe, an early 20th-century American baseball executive and co-owner of the Philadelphia Athletics.
-
D.
Skokie Swift
Skokie Swift is the former name of the Chicago Transit Authority’s Yellow Line rapid transit service connecting Chicago with the suburb of Skokie.
-
E.
The Allen
The Allen is the commonly used local name for Allen Road, a major expressway in Toronto, Ontario, Canada.
- F. None of above.
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_69d7bdef90d48190b46b88270e780946 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d961ef65ac8190aedf9ade3a68e24e |
completed | April 10, 2026, 8:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f671b27790819085f0f03af33f8f21 |
completed | May 2, 2026, 9:50 p.m. |
| NEDg | Description generation | batch_69f6740129688190b286ce7acb4848c7 |
completed | May 2, 2026, 10 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f675249d248190933421df49d3a2ab |
completed | May 2, 2026, 10:05 p.m. |
Created at: April 9, 2026, 5:22 p.m.