Triple
T14191579
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sexy Beast |
E351724
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Don Logan |
E663116
|
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: Don Logan | Statement: [Sexy Beast, mainCharacter, Don Logan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Don Logan Context triple: [Sexy Beast, mainCharacter, Don Logan]
-
A.
Don Logan
chosen
Don Logan is a volatile and menacing criminal character from the British film "Sexy Beast," best known for Ben Kingsley’s intense, Oscar-nominated performance.
-
B.
Mike Logan
Mike Logan is a tough, impulsive New York City detective from the Law & Order franchise known for his streetwise attitude and occasional clashes with authority.
-
C.
Ben Logan
Ben Logan is a fictional character featured in the film "Erased," for whom the movie’s score includes a dedicated musical theme.
-
D.
Robert Logan
Robert Logan is an American actor best known for his roles in 1970s and 1980s adventure and family films such as the "Wilderness Family" series.
-
E.
Tom Kilpatrick
Tom Kilpatrick was a screenwriter best known for his work on the 1940 science fiction horror film "Dr. Cyclops."
- 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_69d827894ac0819097803e57f3227b23 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de61df628c8190ba3f557e2128dce5 |
completed | April 14, 2026, 3:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd7a2fdd7c8190b2ebf5a18c8039f2 |
completed | May 8, 2026, 5:52 a.m. |
Created at: April 10, 2026, 1:04 a.m.