Triple
T21536131
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | House on Haunted Hill |
E531353
|
entity |
| Predicate | musicBy |
P1952
|
FINISHED |
| Object | Von Dexter |
—
|
NE NERFINISHED |
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: Von Dexter | Statement: [House on Haunted Hill, musicBy, Von Dexter]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Von Dexter Context triple: [House on Haunted Hill, musicBy, Von Dexter]
-
A.
Von Dexter
chosen
Von Dexter was a film composer best known for scoring the 1960 horror movie "13 Ghosts."
-
B.
Dexter Wiggles
Dexter Wiggles is a hip-hop artist best known for contributing a featured verse to the Wu-Tang Clan album "8 Diagrams."
-
C.
Dexter
Dexter is a boy genius and secret inventor who stars as the protagonist of the animated television series "Dexter's Laboratory."
-
D.
Dexter
Dexter is a small town in Penobscot County, Maine, known for its rural character and local community-centered schools.
-
E.
Dexter
Dexter is a critically acclaimed American crime drama television series that follows a Miami forensic blood-spatter analyst who leads a secret life as a vigilante serial killer.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c45e5b8881908ac18fc2f493b114 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee9d0e5a9c8190894ec3666d3296aa |
completed | April 26, 2026, 11:17 p.m. |
Created at: April 16, 2026, 6:27 p.m.