Triple
T3549649
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Don |
E75078
|
entity |
| Predicate | hasDiminutive |
P456
|
FINISHED |
| Object | Donny |
E127650
|
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: Donny | Statement: [Don, hasDiminutive, Donny]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Donny Context triple: [Don, hasDiminutive, Donny]
-
A.
Donny
chosen
Donny is a colloquial nickname for Doncaster Rovers Football Club, an English professional football team based in Doncaster, South Yorkshire.
-
B.
Donnie
Donnie is the nickname of Adonis Creed, the central boxer protagonist in the later films of the Rocky/Creed franchise.
-
C.
Donnie Wilson
Donnie Wilson is a skilled and street-smart member of an elite Los Angeles County Sheriff's Department unit in the action-crime film "Den of Thieves."
-
D.
Donnie Shell
Donnie Shell is a former NFL safety best known for his hard-hitting play and key role in the Pittsburgh Steelers’ dominant 1970s dynasty, earning multiple Pro Bowl selections and induction into the Pro Football Hall of Fame.
-
E.
Michael Dorsey
Michael Dorsey is the struggling, perfectionist New York actor who disguises himself as a woman to land a soap-opera role in the 1982 film "Tootsie."
- 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_69ad85d33c6c819081d5ac1df13b5680 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbfd38c8c8190a4591689ad57c998 |
completed | March 8, 2026, 6:28 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b432fdda488190a31f74e80685c121 |
completed | March 13, 2026, 3:53 p.m. |
Created at: March 8, 2026, 3:20 p.m.