Triple
T15133102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | En Vogue |
E361470
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Hold On
"Hold On" is a 1990 R&B hit single by En Vogue that became one of their signature songs and helped establish the group’s mainstream success.
|
E1141931
|
NE FINISHED |
How this triple was built (4 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: Hold On | Statement: [En Vogue, notableWork, Hold On]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hold On Context triple: [En Vogue, notableWork, Hold On]
-
A.
Hold On
"Hold On" is a song featured on the album *Epistles of Mama* by Ghanaian dancehall and reggae artist Stonebwoy.
-
B.
Hold On
"Hold On" is a 1987 country-rock album by the Nitty Gritty Dirt Band that features their hit single "Fishin' in the Dark."
-
C.
Hold On
"Hold On" is an R&B/soul song by American singer-songwriter Dwele, showcasing his smooth vocals and introspective, melodic style.
-
D.
Hold On
"Hold On" is a 1982 rock song by Santana that blends Latin-influenced guitar work with melodic pop-rock elements and became one of the band's notable hits of the early 1980s.
-
E.
Hold On
"Hold On" is a soulful ballad by Adele from her 2021 album "30," reflecting themes of resilience and emotional healing.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Hold On Triple: [En Vogue, notableWork, Hold On]
Generated description
"Hold On" is a 1990 R&B hit single by En Vogue that became one of their signature songs and helped establish the group’s mainstream success.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Hold On Target entity description: "Hold On" is a 1990 R&B hit single by En Vogue that became one of their signature songs and helped establish the group’s mainstream success.
-
A.
Hold On
"Hold On" is a song by the French electronic music duo Justice, known for their distinctive blend of electro, rock, and disco influences.
-
B.
Hold On
"Hold On" is a 1982 rock song by Santana that blends Latin-influenced guitar work with melodic pop-rock elements and became one of the band's notable hits of the early 1980s.
-
C.
Hold On
"Hold On" is a song by Canadian singer-songwriter Sarah McLachlan, known for its emotional depth and inclusion on her acclaimed 1993 album *Fumbling Towards Ecstasy*.
-
D.
Hold On
"Hold On" is a progressive rock song by the English band Yes from their 1983 album 90125.
-
E.
Hold On
"Hold On" is a critically acclaimed blues-rock song by American band Alabama Shakes, known for Brittany Howard's powerful vocals and its role in bringing the band widespread recognition.
- F. None of above. chosen
Provenance (5 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_69d85a06450081909c5a14ea9851a15e |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e005b29a4c819087f8818e3f5788f5 |
completed | April 15, 2026, 9:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fec88096f081908897fd1c5362c274 |
completed | May 9, 2026, 5:39 a.m. |
| NEDg | Description generation | batch_69feca4643dc8190af82f6c2f9133e2a |
completed | May 9, 2026, 5:46 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69fecb0459008190888043ab25bae96b |
completed | May 9, 2026, 5:49 a.m. |
Created at: April 10, 2026, 3:06 a.m.