Triple
T18092518
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Don DeVito |
E433005
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Street-Legal |
—
|
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: Street-Legal | Statement: [Don DeVito, notableWork, Street-Legal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Street-Legal Context triple: [Don DeVito, notableWork, Street-Legal]
-
A.
Street-Legal
chosen
Street-Legal is Bob Dylan’s 1978 studio album known for its fuller, more polished rock sound and introspective, often spiritually tinged lyrics.
-
B.
Street Legal
Street Legal is a Canadian legal drama television series that follows the professional and personal lives of a group of Toronto-based lawyers.
-
C.
Licensed to Drive
"Licensed to Drive" is a song by the American rock band Black Mountain.
-
D.
Town of Legal
The Town of Legal is a small francophone-influenced community in central Alberta, Canada, recognized for its outdoor murals and rural character.
-
E.
Legit
"Legit" is a track from Nas's acclaimed hip-hop album "King's Disease III," showcasing his reflective lyricism and mature storytelling.
- 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_69d8b907d05c819083cc3bd6021089e6 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4dd1972a881908072990de0715547 |
completed | April 19, 2026, 1:48 p.m. |
Created at: April 10, 2026, 10:27 a.m.