Triple
T18333403
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mac Eliot |
E439205
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Bill Duke |
—
|
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: Bill Duke | Statement: [Mac Eliot, portrayedBy, Bill Duke]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bill Duke Context triple: [Mac Eliot, portrayedBy, Bill Duke]
-
A.
Bill Duke
chosen
Bill Duke is an American actor and director known for his imposing presence and roles in films such as "Predator," "Commando," and "Menace II Society."
-
B.
Richard Barr
Richard Barr was an American theater and film producer known for his influential work on Broadway and his collaborations on notable plays and adaptations in the mid-20th century.
-
C.
Kirk Dunn
Kirk Dunn is a technology executive and entrepreneur best known as a co-founder of the big data software company Cloudera.
-
D.
Roger E. Mosley
Roger E. Mosley was an American actor best known for his role as helicopter pilot Theodore "T.C." Calvin on the television series "Magnum, P.I."
-
E.
James Gardner
James Gardner is a relatively common personal name shared by multiple notable individuals across fields such as politics, the arts, and academia.
- 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_69d8b9175fec8190af865699b4e64d8c |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50ecbc76c8190a80c0c8c8bce1cbd |
completed | April 19, 2026, 5:20 p.m. |
Created at: April 10, 2026, 10:36 a.m.