Triple
T18750799
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paul Daniels |
E458517
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object |
Gary Daniels
Gary Daniels is the son of the late British magician and television entertainer Paul Daniels.
|
E1341301
|
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: Gary Daniels | Statement: [Paul Daniels, hasChild, Gary Daniels]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gary Daniels Context triple: [Paul Daniels, hasChild, Gary Daniels]
-
A.
Michael Dokes
Michael Dokes was an American professional heavyweight boxer and former WBA heavyweight champion known for his fast hands and notable fights during the 1980s and early 1990s.
-
B.
Ken Duken
Ken Duken is a German actor and director known for his work in both domestic and international film and television productions.
-
C.
Gary Stevens
Gary Stevens is a Hall of Fame American jockey and occasional actor, known both for his illustrious horse racing career and his role in the film "Seabiscuit."
-
D.
Phil Rogers
Phil Rogers is an American sportswriter and baseball analyst known for his extensive coverage of Major League Baseball and authorship of several books on the sport.
-
E.
Tony Denison
Tony Denison is an American actor best known for his role as Detective Andy Flynn on the crime dramas "The Closer" and its spin-off "Major Crimes."
- 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: Gary Daniels Triple: [Paul Daniels, hasChild, Gary Daniels]
Generated description
Gary Daniels is the son of the late British magician and television entertainer Paul Daniels.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Gary Daniels Target entity description: Gary Daniels is the son of the late British magician and television entertainer Paul Daniels.
-
A.
Michael Dokes
Michael Dokes was an American professional heavyweight boxer and former WBA heavyweight champion known for his fast hands and notable fights during the 1980s and early 1990s.
-
B.
Ken Duken
Ken Duken is a German actor and director known for his work in both domestic and international film and television productions.
-
C.
Gary Stevens
Gary Stevens is a Hall of Fame American jockey and occasional actor, known both for his illustrious horse racing career and his role in the film "Seabiscuit."
-
D.
Phil Rogers
Phil Rogers is an American sportswriter and baseball analyst known for his extensive coverage of Major League Baseball and authorship of several books on the sport.
-
E.
Tony Denison
Tony Denison is an American actor best known for his role as Detective Andy Flynn on the crime dramas "The Closer" and its spin-off "Major Crimes."
- 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_69d8d394dc308190b6725073f5db324c |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e579ec71cc8190bb6d3fa6cca6dc8c |
completed | April 20, 2026, 12:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a053d36fc908190b3193d52ce4504ce |
completed | May 14, 2026, 3:10 a.m. |
| NEDg | Description generation | batch_6a053e216ce0819093f0e9e9b707fca8 |
completed | May 14, 2026, 3:14 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a053ed266a481908dc9ff85e1d7cf4f |
completed | May 14, 2026, 3:17 a.m. |
Created at: April 10, 2026, 11:51 a.m.