Triple
T23273125
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Back on the Streets |
E588341
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Hurricane |
—
|
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: Hurricane | Statement: [Back on the Streets, hasPart, Hurricane]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hurricane Context triple: [Back on the Streets, hasPart, Hurricane]
-
A.
Hurricane
"Hurricane" is a protest song by Bob Dylan that narrates and condemns the wrongful imprisonment of boxer Rubin "Hurricane" Carter.
-
B.
Hurricane
Hurricane is the mascot representing Morristown-Hamblen High School East’s athletic teams and school spirit.
-
C.
Hurricane
"Hurricane" is a song by American rapper and producer Kanye West, featured on his 2021 album *Donda* and known for its atmospheric production and guest vocals from The Weeknd and Lil Baby.
-
D.
Hurricane
chosen
Hurricane is an American hard rock and heavy metal band that gained popularity in the 1980s Los Angeles music scene.
-
E.
Hurricane
"Hurricane" is a notable song by Special Rider Music, recognized as one of the key works associated with the artist.
- 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_69e25d148adc819088efbf42672604e9 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f19575d8988190a8f8496f9110ce8c |
completed | April 29, 2026, 5:21 a.m. |
Created at: April 17, 2026, 4:47 p.m.