Triple
T19771503
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kevin |
E474898
|
entity |
| Predicate | hasDiminutive |
P456
|
FINISHED |
| Object | Kevvie |
—
|
NE NERFINISHED |
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: Kevvie | Statement: [Kevin, hasDiminutive, Kevvie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kevvie Context triple: [Kevin, hasDiminutive, Kevvie]
-
A.
Kevvy
chosen
Kevvy is a familiar or affectionate diminutive form of the given name Kevin.
-
B.
Kev
Kev is the central protagonist of the film "Beautiful Girls," around whom the story’s themes of friendship, love, and coming-of-age revolve.
-
C.
Kev
Kev is a character from the play "Bengal Tiger at the Baghdad Zoo," which explores the psychological and moral fallout of the Iraq War.
-
D.
Kev
Kev is a common shortened form of the given name Kevin, often used informally or as a nickname.
-
E.
Keke
"Keke" is a hip-hop single by rapper Tekashi 6ix9ine, known for its aggressive style and collaboration with fellow New York artists.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e51a43a08190956bc6df13c91a77 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6535bd8c0819097671783962b6bc5 |
completed | April 20, 2026, 4:25 p.m. |
Created at: April 10, 2026, 1:48 p.m.