Triple
T20816331
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bo Derek |
E512447
|
entity |
| Predicate | partner |
P1136
|
FINISHED |
| Object | John Corbett |
—
|
NE NERFINISHED |
How this triple was built (2 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 Corbett | Statement: [Bo Derek, partner, John Corbett]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Corbett Context triple: [Bo Derek, partner, John Corbett]
-
A.
John Corbett
chosen
John Corbett is an American actor and country music singer best known for his roles in "Sex and the City," "My Big Fat Greek Wedding," and various television and film projects.
-
B.
Ted McGinley
Ted McGinley is an American actor best known for his roles on television series such as "Married... with Children," "Happy Days," and "The Love Boat."
-
C.
John Kassir
John Kassir is an American actor and comedian best known for voicing the Crypt Keeper in the HBO series "Tales from the Crypt."
-
D.
Vince Downey
Vince Downey is the hyper-competitive, long-reigning "Employee of the Month" at a discount warehouse store in the 2006 comedy film of the same name.
-
E.
Justin Lader
Justin Lader is an American screenwriter best known for his work on character-driven, genre-blending films such as the surreal romantic drama "The One I Love."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4cd25088190b48ca9700cd24efc |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2f3473c81908c43a2ec242b1acd |
completed | April 21, 2026, 12:21 a.m. |
Created at: April 16, 2026, 12:41 p.m.