Triple
T3197135
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saboteur |
E66960
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | Frank Skinner |
E315135
|
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: Frank Skinner | Statement: [Saboteur, musicBy, Frank Skinner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frank Skinner Context triple: [Saboteur, musicBy, Frank Skinner]
-
A.
Frank Skinner
chosen
Frank Skinner was an American film composer best known for his prolific work scoring Hollywood movies during the mid-20th century, particularly for Universal Pictures.
-
B.
Harry Enfield
Harry Enfield is an English comedian, actor, and writer best known for his influential sketch shows and memorable comic characters on British television.
-
C.
Tony Robinson
Tony Robinson is a British actor, comedian, and presenter best known for playing Baldrick in the historical sitcom series "Blackadder."
-
D.
Danny Baker
Danny Baker is a British broadcaster and writer known for his eclectic radio shows, television presenting, and autobiographical books.
-
E.
Jimmy Carr
Jimmy Carr is a British stand-up comedian and television presenter known for his deadpan delivery, dark humor, and hosting numerous UK panel shows.
- 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_69ad8588ba18819086a10951c32ecb80 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada7192994819084817307065a25e2 |
completed | March 8, 2026, 4:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b24bb7cd488190ae95c140d9cda296 |
completed | March 12, 2026, 5:14 a.m. |
Created at: March 8, 2026, 3:07 p.m.