Triple
T9997710
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Derek Charles |
E197243
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Idris Elba |
E6094
|
NE FINISHED |
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: Idris Elba | Statement: [Derek Charles, portrayedBy, Idris Elba]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Idris Elba Context triple: [Derek Charles, portrayedBy, Idris Elba]
-
A.
Idris Elba
chosen
Idris Elba is a British actor, producer, and musician known for his roles in projects such as "Luther," "The Wire," and numerous major Hollywood films.
-
B.
Djimon Hounsou
Djimon Hounsou is a Beninese-American actor and former model known for powerful supporting roles in films such as "Amistad," "Gladiator," and "Blood Diamond."
-
C.
Ving Rhames
Ving Rhames is an American actor best known for his deep voice and memorable roles in films such as the Mission: Impossible series and Pulp Fiction.
-
D.
Colin Freeman
Colin Freeman is the former husband of American singer and actress Lorna Luft, daughter of Judy Garland.
-
E.
David Oyelowo
David Oyelowo is a British-Nigerian actor known for his powerful performances in film and television, particularly in biographical and historical dramas.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca82f3b61c81908ecc2c1c96dbc2e4 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdcc8aa1a881909879a694496f11a5 |
completed | April 2, 2026, 1:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d258336ab8819098d4878b8c106d86 |
completed | April 5, 2026, 12:40 p.m. |
Created at: March 30, 2026, 8:51 p.m.