Triple
T12410587
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | African Giant |
E296502
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Anybody (song) |
E294490
|
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: Anybody (song) | Statement: [African Giant, hasPart, Anybody (song)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Anybody (song) Context triple: [African Giant, hasPart, Anybody (song)]
-
A.
Anybody
chosen
"Anybody" is a popular Afro-fusion song by Nigerian artist Burna Boy, known for its smooth blend of Afrobeat rhythms and socially conscious lyrics.
-
B.
Somebody
"Somebody" is a song featured on the album "The Lover in Me."
-
C.
Nobody (song)
"Nobody" is a landmark early 20th-century American song popularized by vaudeville performer Bert Williams, known for its melancholic humor and commentary on loneliness and social neglect.
-
D.
Looking for Somebody
"Looking for Somebody" is a blues-rock track by guitarist Gary Moore from his Peter Green tribute album "Blues for Greeny."
-
E.
Any Time
"Any Time" is a popular traditional pop song closely associated with American singer Eddie Fisher, who helped make it a hit in the early 1950s.
- 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_69d6ad9f464c81909db36d7e96e34b9e |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94d4b86c88190afba0de15b34eee9 |
completed | April 10, 2026, 7:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6348af5a8819083a075d145b15fd4 |
completed | May 2, 2026, 5:29 p.m. |
Created at: April 8, 2026, 9:55 p.m.