Triple
T9488918
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Irvin |
E228832
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Irvin |
E228832
|
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: Irvin | Statement: [Michael Irvin, familyName, Irvin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Irvin Context triple: [Michael Irvin, familyName, Irvin]
-
A.
Irvin
chosen
Irvin is a surname most prominently associated with former NFL wide receiver and sports commentator Michael Irvin.
-
B.
Bivins
Bivins is a surname most notably associated with Michael Bivins, an American singer, rapper, and music executive known for his work with New Edition and Bell Biv DeVoe.
-
C.
Guston
Guston is a small village and civil parish in the Dover District of Kent, England.
-
D.
Al Hibbler
Al Hibbler was an American baritone jazz and pop singer best known for his work with Duke Ellington’s orchestra and his hit recordings in the 1940s and 1950s.
-
E.
Dobie
Dobie is the first name of the fictional character Dobie Gillis, a typical American teenager featured in Max Shulman’s stories and the TV series "The Many Loves of Dobie Gillis."
- 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_69ca847424f081908180305555139f7a |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd80c5a05c8190b97d34f010e60ca1 |
completed | April 1, 2026, 8:32 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d12d18fd908190b562fa0a8dad7c63 |
completed | April 4, 2026, 3:24 p.m. |
Created at: March 30, 2026, 7:55 p.m.