Triple
T12004857
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harlem Shuffle |
E285755
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Earl Nelson |
E210974
|
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: Earl Nelson | Statement: [Harlem Shuffle, writer, Earl Nelson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Earl Nelson Context triple: [Harlem Shuffle, writer, Earl Nelson]
-
A.
Earl Nelson
Earl Nelson is a hereditary British peerage title created to honor Admiral Horatio Nelson, with its holders traditionally also bearing the Sicilian title Duke of Bronte.
-
B.
Benjamin Earl Nelson
chosen
Benjamin Earl Nelson, better known as Ben E. King, was an American soul and R&B singer famed for his classic hit "Stand by Me."
-
C.
Nelson Johnson
Nelson Johnson is an American author and former judge best known for writing the nonfiction book that inspired the television series "Boardwalk Empire."
-
D.
Cecil Doggette
Cecil Doggette is a former American football defensive back who played in the NFL and NFL Europe, notably for teams such as the New York Jets and the Frankfurt Galaxy.
-
E.
Earl Reser
Earl Reser is an American businessman best known as the founder of Reser’s Fine Foods, a major producer of prepared salads and deli foods.
- 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_69d6ab45a368819084fce08bf0dc3705 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903c481a48190b311d6809808ef1b |
completed | April 10, 2026, 2:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f76b9112948190a0dd747a67f8206a |
completed | May 3, 2026, 3:36 p.m. |
Created at: April 8, 2026, 9:46 p.m.