Triple
T14611697
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brian McKnight (album) |
E342975
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | “My Prayer” |
E648517
|
NE FINISHED |
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: “My Prayer” | Statement: [Brian McKnight (album), hasPart, “My Prayer”]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: “My Prayer” Context triple: [Brian McKnight (album), hasPart, “My Prayer”]
-
A.
My Prayer
chosen
"My Prayer" is a 1956 doo-wop ballad by The Platters that became one of their signature hits, noted for its lush harmonies and romantic style.
-
B.
I Pray for You
"I Pray for You" is a track by rapper Pusha T featured on his critically acclaimed album "It's Almost Dry."
-
C.
Pray for Me
"Pray for Me" is an R&B/soul song by American singer Anthony Hamilton, known for its heartfelt lyrics and gospel-infused sound.
-
D.
Pray for Me
"Pray for Me" is a track by Snoop Dogg featured on his album "Doggumentary."
-
E.
Pray for Me
"Pray for Me" is a song by English singer-songwriter Laura Marling from her critically acclaimed 2013 album "Once I Was an Eagle."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d822dec68081908c2553145c4051dc |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb450e6588190a94488d8e71888c8 |
completed | April 14, 2026, 9:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fda91f437c8190ada4d1c3708faedd |
completed | May 8, 2026, 9:13 a.m. |
Created at: April 10, 2026, 1:25 a.m.