Triple
T4176548
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A Fish Called Wanda |
E86490
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | John Du Prez |
E379122
|
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: John Du Prez | Statement: [A Fish Called Wanda, musicBy, John Du Prez]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Du Prez Context triple: [A Fish Called Wanda, musicBy, John Du Prez]
-
A.
John Du Prez
chosen
John Du Prez is a British composer and musician best known for his film scores and long-running collaboration with the comedy group Monty Python.
-
B.
Michael Codron
Michael Codron is a prominent British theatre producer known for championing new playwrights and staging influential West End productions.
-
C.
Michael Ballhaus
Michael Ballhaus was a renowned German cinematographer celebrated for his dynamic camera work and frequent collaborations with director Martin Scorsese.
-
D.
Marc Arnold
Marc Arnold is a relatively obscure individual whose primary public mention is as a notable bearer of the surname Arnold.
-
E.
Richard Marks
Richard Marks was an American film editor known for his work on numerous acclaimed movies, including the culinary drama "Julie & Julia."
- 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_69aed93de98c8190ad838ce507b77c8a |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af02eaa0d08190a3b805c64ef76a0c |
completed | March 9, 2026, 5:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b57f564c9c8190bfc321c8ec2dac14 |
completed | March 14, 2026, 3:31 p.m. |
Created at: March 9, 2026, 3:45 p.m.