Triple
T1813940
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DeVon Harris |
E40392
|
entity |
| Predicate | knownFor |
P22
|
FINISHED |
| Object | So High |
E204541
|
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: So High | Statement: [DeVon Harris, knownFor, So High]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: So High Context triple: [DeVon Harris, knownFor, So High]
-
A.
So High
"So High" is an R&B/soul song by John Legend from his debut album "Get Lifted."
-
B.
So High
chosen
"So High" is a creative work associated with DeVon Harris, likely recognized as one of his most prominent or influential projects.
-
C.
How Low
"How Low" is a popular hip-hop single by American rapper Ludacris, known for its catchy hook and heavy club-oriented production.
-
D.
Reach Higher
Reach Higher is an education initiative launched by Michelle Obama to inspire and support young people in pursuing and completing postsecondary education.
-
E.
If Not Higher
"If Not Higher" is a classic Yiddish short story by I. L. Peretz that gently satirizes religious hypocrisy while celebrating genuine piety and compassion.
- 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_69a88643a3388190a612f2ebe1fb29e7 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69aa65c905ec8190bea7cd72d218487a |
completed | March 6, 2026, 5:27 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69adc9aa4c5881908b21829dda45da5a |
completed | March 8, 2026, 7:10 p.m. |
Created at: March 4, 2026, 7:32 p.m.