Triple
T18591017
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | How High the Moon |
E454366
|
entity |
| Predicate | usedAsBasisFor |
P7051
|
FINISHED |
| Object | How High |
—
|
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: How High | Statement: [How High the Moon, usedAsBasisFor, How High]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: How High Context triple: [How High the Moon, usedAsBasisFor, How High]
-
A.
How High
chosen
How High is a 2001 stoner comedy film starring Method Man and Redman as underachieving friends who use a supernatural strain of marijuana to succeed at Harvard University.
-
B.
So High
"So High" is an R&B/soul song by John Legend from his debut album "Get Lifted."
-
C.
So High
"So High" is a creative work associated with DeVon Harris, likely recognized as one of his most prominent or influential projects.
-
D.
When on High
"When on High" is the traditional English rendering of the opening words and common title of the ancient Babylonian creation epic Enuma Elish.
-
E.
Too High
"Too High" is a socially conscious soul and funk song by Stevie Wonder that opens his acclaimed 1973 album Innervisions, addressing drug abuse through inventive lyrics and complex musical arrangements.
- 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_69d8d38ae7e081908a98df1251842402 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e545b5bc688190bdfe3911ac6b2d76 |
completed | April 19, 2026, 9:14 p.m. |
Created at: April 10, 2026, 11:44 a.m.