Triple
T13119099
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Witch |
E311676
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | Mark Korven |
E421850
|
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 Korven | Statement: [The Witch, musicBy, Mark Korven]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Korven Context triple: [The Witch, musicBy, Mark Korven]
-
A.
Mark Korven
chosen
Mark Korven is a Canadian film and television composer best known for his unsettling, atmospheric scores for horror projects such as The Witch and The Lighthouse.
-
B.
Mark Kohr
Mark Kohr is an American music video director known for his work with prominent alternative rock bands in the 1990s.
-
C.
Kurt Voss
Kurt Voss is an American filmmaker and screenwriter known for his work in independent cinema, often exploring gritty, character-driven stories.
-
D.
Mark Okerstrom
Mark Okerstrom is a Canadian business executive best known for serving as the former CEO of Expedia Group.
-
E.
John Kamps
John Kamps is an American screenwriter best known for co-writing the family science fiction film "Zathura: A Space Adventure."
- 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_69d806a9fe888190b081e2d9ea665d6c |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98196e69081909111407ee3d9f08e |
completed | April 10, 2026, 11:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f79d3398b08190a0fc4b6044576e0a |
completed | May 3, 2026, 7:08 p.m. |
Created at: April 9, 2026, 9:06 p.m.