Triple
T16987248
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Don Mattingly |
E412100
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Donald |
E675733
|
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: Donald | Statement: [Don Mattingly, givenName, Donald]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Donald Context triple: [Don Mattingly, 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 the English actor and theatre manager Donald Wolfit.
-
C.
Donald
Donald is the given name of Donald A. Norman, a prominent cognitive scientist and design theorist known for his influential work on user-centered design.
-
D.
Donald
Donald is the given first name of American film producer Don Simpson, known for his work on blockbuster Hollywood movies in the 1980s and 1990s.
-
E.
Donald
chosen
Donald is the given first name of Don Drysdale, the Hall of Fame Major League Baseball pitcher known for his dominant career with the Los Angeles Dodgers.
- 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_69d886ca8f348190812768ea8d5055ce |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d27b58908190a643bcbd105b1849 |
completed | April 18, 2026, 6:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00dc12e308819093e7f8933cdd6ba9 |
completed | May 10, 2026, 7:27 p.m. |
Created at: April 10, 2026, 5:32 a.m.