Triple
T20819187
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom Kelly |
E512526
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | So Emotional |
—
|
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: So Emotional | Statement: [Tom Kelly, notableWork, So Emotional]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: So Emotional Context triple: [Tom Kelly, notableWork, So Emotional]
-
A.
So Emotional
chosen
"So Emotional" is a 1987 dance-pop song by Whitney Houston that became one of her number-one hits on the Billboard Hot 100.
-
B.
Emotional (album)
Emotional is the platinum-certified 2000 debut R&B album by singer Carl Thomas, best known for its hit single "I Wish."
-
C.
Deep Feeling
"Deep Feeling" is a song best known as the B-side to Chuck Berry's 1957 single "School Day," featuring a distinctive instrumental guitar arrangement.
-
D.
One Emotion
One Emotion is a 1994 country music album by American singer-songwriter Clint Black, featuring a blend of traditional and contemporary country styles.
-
E.
Emotional
"Emotional" is a pop-R&B single by American Idol alumna Diana DeGarmo that showcases her powerful vocal style and post-show recording career.
- 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_69e0b4ce39108190a6e8e5df4f1c8dc5 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2f5b1e08190a9c26f76bd544b68 |
completed | April 21, 2026, 12:21 a.m. |
Created at: April 16, 2026, 12:41 p.m.