Triple
T11747503
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tsotsi |
E279321
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | Mark Kilian |
E878895
|
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: Mark Kilian | Statement: [Tsotsi, musicBy, Mark Kilian]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Kilian Context triple: [Tsotsi, musicBy, Mark Kilian]
-
A.
Mark Kilian
chosen
Mark Kilian is a South African-born film composer known for scoring numerous Hollywood movies and television projects.
-
B.
Victor Kilian
Victor Kilian was an American character actor known for his prolific work in film and television from the 1920s through the 1970s.
-
C.
Bruno Coulais
Bruno Coulais is a French composer best known for his atmospheric and innovative film scores, particularly in European cinema and animation.
-
D.
Vaughan Oliver
Vaughan Oliver was a renowned British graphic designer best known for his influential, surreal album artwork for the 4AD record label.
-
E.
Will Scheffer
Will Scheffer is an American television writer and producer best known as the co-creator of the HBO drama series "Big Love."
- 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_69d6ab01038c819080714901502c84fc |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a50763a081908597da118bd0a64e |
completed | April 10, 2026, 7:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f019f5f29c81909d80a9e6127ec6ef |
completed | April 28, 2026, 2:22 a.m. |
Created at: April 8, 2026, 9:41 p.m.