Triple
T1342632
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dionne Warwick |
E28499
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Walk On By |
E120443
|
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: Walk On By | Statement: [Dionne Warwick, notableWork, Walk On By]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Walk On By Context triple: [Dionne Warwick, notableWork, Walk On By]
-
A.
Walk On By
chosen
"Walk On By" is a classic 1964 soul-pop song written by Burt Bacharach and Hal David, most famously recorded by Dionne Warwick and widely covered and sampled across genres.
-
B.
Walk On
"Walk On" is a U2 song known as an anthemic tribute to courage and perseverance, originally inspired by Burmese political leader Aung San Suu Kyi.
-
C.
So Gone
"So Gone" is an R&B song best known as a 2003 hit single by Monica, produced by Missy Elliott and Kanye West.
-
D.
Keep My Spirit Alive
"Keep My Spirit Alive" is a gospel-influenced hip-hop track from Kanye West’s album *Donda*, featuring introspective lyrics and guest verses from collaborators.
-
E.
Hold On
"Hold On" is a song featured on the album "Warning" by the American punk rock band Green Day.
- 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_69a49854eb3481908c7d56b2e449a290 |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c2174d048190a6e9380df302265f |
completed | March 1, 2026, 10:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69acc632cbc88190a64897f1b101c699 |
completed | March 8, 2026, 12:43 a.m. |
Created at: March 1, 2026, 7:56 p.m.