Triple
T22347977
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Herb Jaffe |
E552444
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Madhouse |
—
|
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: Madhouse | Statement: [Herb Jaffe, notableWork, Madhouse]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Madhouse Context triple: [Herb Jaffe, notableWork, Madhouse]
-
A.
Madhouse
Madhouse was a short-lived jazz-fusion side project created by Prince in the mid-1980s, known for its instrumental albums blending funk, jazz, and experimental sounds.
-
B.
Madhouse
"Madhouse" is a 1985 thrash metal song by the American band Anthrax, known for its fast tempo, aggressive riffs, and themes of insanity.
-
C.
Madhouse
Madhouse is a renowned Japanese animation studio known for producing a wide range of influential anime series and films.
-
D.
Madhouse
chosen
"Madhouse" is a 1990 American comedy film starring John Larroquette and Kirstie Alley, centered on a couple whose lives spiral into chaos when uninvited relatives overrun their home.
-
E.
The Old Madhouse
The Old Madhouse is a novel by British artist and writer William De Morgan, known for its blend of social commentary, psychological insight, and late Victorian humor.
- 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_69e11e4a0ad08190a385b4d343cf6524 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f157995bec819080b8d05fa88704ed |
completed | April 29, 2026, 12:58 a.m. |
Created at: April 16, 2026, 8:43 p.m.