Triple
T19306203
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Graham Evers |
E482834
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Graham Evers |
—
|
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: Graham Evers | Statement: [Graham Evers, name, Graham Evers]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Graham Evers Context triple: [Graham Evers, name, Graham Evers]
-
A.
Graham Evers
chosen
Graham Evers is an individual notable enough to be specifically cited as a bearer of the surname Evers.
-
B.
Graeme Revell
Graeme Revell is a New Zealand-born composer best known for his atmospheric film scores across genres including horror, action, and science fiction.
-
C.
Marc Eversley
Marc Eversley is a Canadian basketball executive known for serving as the general manager of the NBA’s Chicago Bulls.
-
D.
Graham Wylie
Graham Wylie is a British entrepreneur best known as a co-founder of the software company Sage Group and a prominent figure in the UK technology and business community.
-
E.
Graham Walters
Graham Walters is a film producer best known for his work on the acclaimed Pixar animated feature "Finding Nemo."
- 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_69d8e8d04d5c8190baa816986f2b1d1e |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e604c84fe08190869463bdd0324160 |
completed | April 20, 2026, 10:49 a.m. |
Created at: April 10, 2026, 1:31 p.m.