Triple
T18067779
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Randy Goodrum |
E432335
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Broken Hearted Me |
—
|
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: Broken Hearted Me | Statement: [Randy Goodrum, notableWork, Broken Hearted Me]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Broken Hearted Me Context triple: [Randy Goodrum, notableWork, Broken Hearted Me]
-
A.
Broken Hearted Me
chosen
"Broken Hearted Me" is a popular country-pop ballad recorded by Canadian singer Anne Murray that became one of her signature hits in the late 1970s.
-
B.
Brokenhearted
"Brokenhearted" is an R&B ballad by American singer Brandy, best known for its emotional vocals and success as one of the standout hits from her debut album.
-
C.
Broken Heart
"Broken Heart" is a song featured on the album *Shine On*, known for its emotive lyrics and melodic, reflective style.
-
D.
Broken Heart
Broken Heart is a distinctive, heart-shaped red rock formation and popular scenic landmark in the Jeti-Ögüz Gorge of Kyrgyzstan.
-
E.
Breaks My Heart
"Breaks My Heart" is a song featured on the album "After the Storm."
- 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_69d8b9070cac81909fa9473fb1c3f1c7 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4cceb020081909329492591e7b1f2 |
completed | April 19, 2026, 12:39 p.m. |
Created at: April 10, 2026, 10:26 a.m.