Triple
T17490170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Millie Jackson |
E425882
|
entity |
| Predicate | notableSong |
P4
|
FINISHED |
| Object | Hurts So Good |
—
|
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: Hurts So Good | Statement: [Millie Jackson, notableSong, Hurts So Good]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hurts So Good Context triple: [Millie Jackson, notableSong, Hurts So Good]
-
A.
Hurts So Good
"Hurts So Good" is a hit rock song by American singer-songwriter John Mellencamp, known for its catchy chorus and blend of heartland rock and pop.
-
B.
It Hurts So Good
chosen
"It Hurts So Good" is a soulful R&B song written and recorded by Prince Phillip Mitchell that became a widely covered classic in the 1970s.
-
C.
When It Hurts So Bad
"When It Hurts So Bad" is a soulful R&B track by Lauryn Hill that explores the pain and complexity of a toxic relationship.
-
D.
Hurts
"Hurts" is a pop song by British-Lebanese singer-songwriter Mika, known for its emotive lyrics and melodic, theatrical style.
-
E.
It Hurts So Bad
"It Hurts So Bad" is a song by American singer Linda Ronstadt, featured on her 1980 album "Mad Love."
- 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_69d889dccf7481909264a1844a2e9100 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e451d519488190a08da1b529c08445 |
completed | April 19, 2026, 3:53 a.m. |
Created at: April 10, 2026, 5:48 a.m.