Triple
T10660720
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GoldenEye |
E251215
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Joe Don Baker |
E449096
|
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: Joe Don Baker | Statement: [GoldenEye, starring, Joe Don Baker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joe Don Baker Context triple: [GoldenEye, starring, Joe Don Baker]
-
A.
Joe Don Baker
chosen
Joe Don Baker is an American actor best known for his tough-guy roles in films such as "Walking Tall" and multiple James Bond movies.
-
B.
Eric Baker
Eric Baker was a British human rights activist best known as a co-founder of Amnesty International.
-
C.
Greg Reely
Greg Reely is a Canadian record producer and audio engineer best known for his work with industrial, electronic, and alternative rock artists such as Front Line Assembly and Sarah McLachlan.
-
D.
Joe Dukes
Joe Dukes was a prominent American jazz drummer best known for his dynamic work in soul-jazz and hard bop, particularly in organ-led groups.
-
E.
Don Johnson
Don Johnson is an American actor best known for his charismatic leading role in the 1980s TV series "Miami Vice" and numerous film and television appearances.
- 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_69d6aa5b0d2881909584b20efc5877f0 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6e017f97c8190b22765a6f1e6719d |
completed | April 8, 2026, 11:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d97a8cabc88190b430cb08ed0fc515 |
completed | April 10, 2026, 10:32 p.m. |
Created at: April 8, 2026, 9:08 p.m.