Triple
T375984
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Greatest Love of All |
E8373
|
entity |
| Predicate | WhitneyHoustonVersion.awardRecognition |
P11
|
FINISHED |
| Object | nominated for American Music Awards |
—
|
LITERAL 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: nominated for American Music Awards | Statement: [Greatest Love of All, WhitneyHoustonVersion.awardRecognition, nominated for American Music Awards]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: WhitneyHoustonVersion.awardRecognition Context triple: [Greatest Love of All, WhitneyHoustonVersion.awardRecognition, nominated for American Music Awards]
-
A.
awardReceived
chosen
Indicates that an entity has been granted or honored with a specific award or recognition.
-
B.
numberOfAwards
Indicates the total count of awards that have been received by an entity.
-
C.
awardFor
Indicates that something is given or granted as recognition or a prize for a particular achievement, work, or contribution.
-
D.
awardType
Indicates the specific category or kind of award associated with an entity or event.
-
E.
hasAwarded
Indicates that one entity has given or conferred an award to another entity.
- F. None of above.
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_69a2e7f2ec648190b42bc7db424f8109 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ec169a848190a577aa093c878839 |
completed | Feb. 28, 2026, 1:22 p.m. |
| PD | Predicate disambiguation | batch_69a2e96216048190873ae533fa5b864d |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.