Triple
T8527449
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donald Deskey |
E201852
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object |
Donald
Donald is the given name of Donald Deskey, an influential American industrial designer best known for his work on Radio City Music Hall’s interiors.
|
E742099
|
NE FINISHED |
How this triple was built (4 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: Donald | Statement: [Donald Deskey, givenName, Donald]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Donald Context triple: [Donald Deskey, givenName, Donald]
-
A.
Donald
Donald is the given name of Donald W. Riegle Jr., a former United States Senator from Michigan.
-
B.
Donald
Donald is the given name of Don Revie, the renowned English football player and manager best known for his successful tenure at Leeds United.
-
C.
Donald
Donald III of Scotland was a late 11th-century King of Scots who briefly ruled following the death of his brother Malcolm III.
-
D.
Donald
Donald is the surname of Aaron Donald, the dominant American football defensive tackle widely regarded as one of the greatest defensive players in NFL history.
-
E.
Donald
Donald is a fictional character portrayed by American actor Matt Bomer, likely in a film or television production.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Donald Triple: [Donald Deskey, givenName, Donald]
Generated description
Donald is the given name of Donald Deskey, an influential American industrial designer best known for his work on Radio City Music Hall’s interiors.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Donald Target entity description: Donald is the given name of Donald Deskey, an influential American industrial designer best known for his work on Radio City Music Hall’s interiors.
-
A.
Donald
Donald is the given name of Donald F. Othmer, an American chemical engineer, inventor, and co-editor of the influential Kirk-Othmer Encyclopedia of Chemical Technology.
-
B.
Donald
Donald is the given name of Donald Judd, the influential American artist known for his pioneering role in Minimalist sculpture and installation art.
-
C.
Donald
Donald is the given name of Donald Trump, the 45th president of the United States and a prominent businessman and media personality.
-
D.
Donald
Donald is the given first name of influential American jazz musician, arranger, and bandleader Don Redman.
-
E.
Donald
Donald is the given name of Don Revie, the renowned English football player and manager best known for his successful tenure at Leeds United.
- F. None of above. chosen
Provenance (5 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_69ca83228b24819085d22e7dc99f5d94 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe6477100819081fa20cb6b8ea3d7 |
completed | March 31, 2026, 3:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce6d54ef908190970a1010c8018abd |
completed | April 2, 2026, 1:21 p.m. |
| NEDg | Description generation | batch_69ce71cd3320819090f2e09f51493f9a |
completed | April 2, 2026, 1:40 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ce725a4cf081909cd470fd4d7452ca |
completed | April 2, 2026, 1:42 p.m. |
Created at: March 30, 2026, 6:16 p.m.