Triple
T10241268
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fats Waller |
E243597
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Waller |
E813811
|
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: Waller | Statement: [Fats Waller, familyName, Waller]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Waller Context triple: [Fats Waller, familyName, Waller]
-
A.
Waller
chosen
Waller is a surname most notably associated with American author Robert James Waller, known for writing "The Bridges of Madison County."
-
B.
Walling
Walling is a surname most notably associated with William English Walling, an American labor reformer and co-founder of the NAACP.
-
C.
Wallen
Wallen is the colloquial Dutch name for Amsterdam’s famous Red Light District, known for its historic canals, legalized prostitution, and vibrant nightlife.
-
D.
Wardell
Wardell is the given first name of American character actor Ward Bond, known for his prolific roles in classic Hollywood films and Westerns.
-
E.
Wylie
Wylie is a suburban city in the Dallas–Fort Worth metropolitan area in northeastern Texas.
- 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_69d381b0f97c819085c9b45799a5fb7c |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d21f2ae0819098ac60c828dc9cae |
completed | April 7, 2026, 9:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d6f780c7808190993e7c37cb4d18a3 |
completed | April 9, 2026, 12:49 a.m. |
Created at: April 6, 2026, 11:24 a.m.