Triple
T5334370
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Derek |
E123789
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object |
John
John Derek was an American actor, director, and photographer known for his film roles in the 1940s–1960s and for directing and photographing his wife Bo Derek.
|
E512719
|
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 Derek, givenName, John]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Context triple: [John Derek, givenName, John]
-
A.
John
John is the given name of the renowned British mathematician John H. Conway, known for his work in group theory, number theory, and the invention of the Game of Life.
-
B.
John
John is the given name of John Nance Garner, who served as the 32nd vice president of the United States under President Franklin D. Roosevelt.
-
C.
John
John is the given first name of J. Michael Bishop, the American immunologist and Nobel Prize–winning scientist known for his work on oncogenes.
-
D.
John
John is the given name of John H. Hammond Jr., the influential American record producer and talent scout known for discovering and promoting numerous major jazz, blues, and rock musicians.
-
E.
John
John is the given name of John F. Sattler, likely referring to him in a more informal or abbreviated context.
- 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 Derek, givenName, John]
Generated description
John Derek was an American actor, director, and photographer known for his film roles in the 1940s–1960s and for directing and photographing his wife Bo Derek.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: John Target entity description: John Derek was an American actor, director, and photographer known for his film roles in the 1940s–1960s and for directing and photographing his wife Bo Derek.
-
A.
John
John is the birth name of Jack Pickford, a Canadian-born American actor and film director of the silent era and younger brother of Mary Pickford.
-
B.
John
John is the birth name of American actor and filmmaker Jack Nicholson, one of cinema’s most acclaimed and iconic performers.
-
C.
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."
-
D.
John
John is the first name of American filmmaker John Lee Hancock, known for directing and writing several popular Hollywood films.
-
E.
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."
- 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_69bd464b07f8819095aa76577c9829e4 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd85ae52c08190968a5567b7e6b794 |
completed | March 20, 2026, 5:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf188394ec81909a03afe92750e9c1 |
completed | March 21, 2026, 10:15 p.m. |
| NEDg | Description generation | batch_69bf1c6c84b481909c7e650c58961bd7 |
completed | March 21, 2026, 10:32 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69bf1cce6f9881908499ac380f183ffb |
completed | March 21, 2026, 10:33 p.m. |
Created at: March 20, 2026, 2 p.m.