Triple
T20195775
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | So It Is |
E493080
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Mad |
—
|
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: Mad | Statement: [So It Is, hasPart, Mad]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mad Context triple: [So It Is, hasPart, Mad]
-
A.
Mad
chosen
"Mad" is an R&B ballad by American singer Ne-Yo, known for its emotional lyrics about conflict and reconciliation in a relationship.
-
B.
Mad
Mad is a long-running American humor magazine best known for its satirical takes on popular culture, politics, and everyday life.
-
C.
Insanity
"Insanity" is a track by jazz vocalist and songwriter Gregory Porter from his critically acclaimed album "Take Me to the Alley."
-
D.
Insanity
Insanity is a comedic track by the American parody musician "Weird Al" Yankovic, known for its humorous and satirical style.
-
E.
Insanity
"Insanity" is a song by the Japanese rock band Boingo, known for its intense, off-kilter style and darkly energetic sound.
- 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_69da6268a034819081cbd9ea5a1c9475 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66ad8b3cc8190aa9c9c79c552002a |
completed | April 20, 2026, 6:05 p.m. |
Created at: April 11, 2026, 11:37 p.m.