Triple
T4716664
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John William Ferrell |
E104657
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object |
John
John William Ferrell, known professionally as Will Ferrell, is an American actor, comedian, producer, and writer famous for his work on "Saturday Night Live" and numerous comedy films.
|
E104657
|
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: John | Statement: [John William Ferrell, givenName, John]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Context triple: [John William Ferrell, givenName, John]
-
A.
John
John is the given first name of the legendary American professional golfer Byron Nelson, one of the sport’s early great champions.
-
B.
John
John is the husband of Martha Rainsborough.
-
C.
John
John is the given name of American actor John Goodman, renowned for his roles in film, television, and theater.
-
D.
John
John is the given name of John F. Fitzgerald, an American politician who served as mayor of Boston and was the maternal grandfather of President John F. Kennedy.
-
E.
John
John Guillermin was a British film director and producer best known for directing large-scale adventure and disaster films such as "The Towering Inferno" and the 1976 remake of "King Kong."
- 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: John Triple: [John William Ferrell, givenName, John]
Generated description
John William Ferrell, known professionally as Will Ferrell, is an American actor, comedian, producer, and writer famous for his work on "Saturday Night Live" and numerous comedy films.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: John Target entity description: John William Ferrell, known professionally as Will Ferrell, is an American actor, comedian, producer, and writer famous for his work on "Saturday Night Live" and numerous comedy films.
-
A.
John
chosen
John is the first name of American comedian and actor Will Ferrell, known for his work on Saturday Night Live and numerous comedy films.
-
B.
John
John is the given name of the late American comedian and actor John Belushi, famed for his work on "Saturday Night Live" and in films like "Animal House" and "The Blues Brothers."
-
C.
John
John is the given name of the late Canadian actor and comedian John Candy, known for his roles in films like "Planes, Trains and Automobiles" and "Uncle Buck."
-
D.
John
John is the birth name of American actor Jack Lemmon, a celebrated star of classic films such as "Some Like It Hot" and "The Apartment."
-
E.
John
John is the given name of American actor and comedian John Larroquette, best known for his Emmy-winning role on the sitcom "Night Court."
- 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_69bd43ec4a348190bc41afae43375e71 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd640a32ec8190850146957885c3cf |
completed | March 20, 2026, 3:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be39e6428c81909be9bdb314993b1e |
completed | March 21, 2026, 6:25 a.m. |
| NEDg | Description generation | batch_69be3c02014c81908a6f3ed676e5505c |
completed | March 21, 2026, 6:34 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69be3cd64d0c8190b007e9f027185225 |
completed | March 21, 2026, 6:38 a.m. |
Created at: March 20, 2026, 1:18 p.m.