Triple
T272649
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Red Hat |
E5668
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object |
Bob Young
Bob Young is a Canadian entrepreneur best known as the co-founder and former CEO of open-source software company Red Hat.
|
E96032
|
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: Bob Young | Statement: [Red Hat, foundedBy, Bob Young]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bob Young Context triple: [Red Hat, foundedBy, Bob Young]
-
A.
Ted Cheesman
Ted Cheesman was a film editor best known for his work on classic Hollywood productions, including the 1933 monster film "King Kong."
-
B.
Frank Richard Wells
Frank Richard Wells was a son of the famed English writer H. G. Wells.
-
C.
James T. Sutherland
James T. Sutherland was a prominent Canadian hockey executive and historian who played a key role in organizing and promoting the sport, including helping to establish the Hockey Hall of Fame.
-
D.
James Rogers
James Rogers is a common personal name shared by numerous individuals across various fields, including politics, academia, sports, and the arts.
-
E.
John R. Steelman
John R. Steelman was an American administrator and labor mediator who served as a top aide to President Harry S. Truman and became one of the most influential behind-the-scenes figures in the postwar White House.
- 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: Bob Young Triple: [Red Hat, foundedBy, Bob Young]
Generated description
Bob Young is a Canadian entrepreneur best known as the co-founder and former CEO of open-source software company Red Hat.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bob Young Target entity description: Bob Young is a Canadian entrepreneur best known as the co-founder and former CEO of open-source software company Red Hat.
-
A.
Ted Cheesman
Ted Cheesman was a film editor best known for his work on classic Hollywood productions, including the 1933 monster film "King Kong."
-
B.
Frank Richard Wells
Frank Richard Wells was a son of the famed English writer H. G. Wells.
-
C.
James T. Sutherland
James T. Sutherland was a prominent Canadian hockey executive and historian who played a key role in organizing and promoting the sport, including helping to establish the Hockey Hall of Fame.
-
D.
James Rogers
James Rogers is a common personal name shared by numerous individuals across various fields, including politics, academia, sports, and the arts.
-
E.
John R. Steelman
John R. Steelman was an American administrator and labor mediator who served as a top aide to President Harry S. Truman and became one of the most influential behind-the-scenes figures in the postwar White House.
- 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_69a25853594c8190b05ec3a586ec88bf |
completed | Feb. 28, 2026, 2:52 a.m. |
| NER | Named-entity recognition | batch_69a25dcf667c8190a7b8630fe67b9a90 |
completed | Feb. 28, 2026, 3:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a76d6061508190b6fd3c907107fc63 |
completed | March 3, 2026, 11:23 p.m. |
| NEDg | Description generation | batch_69a78328882881908d25e2fec0909da6 |
completed | March 4, 2026, 12:56 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a7839196fc819097800de8c360cef9 |
completed | March 4, 2026, 12:57 a.m. |
Created at: Feb. 28, 2026, 2:57 a.m.