Triple
T17598757
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MySQL AB |
E428638
|
entity |
| Predicate | notableEmployee |
P304
|
FINISHED |
| Object | David Axmark |
—
|
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: David Axmark | Statement: [MySQL AB, notableEmployee, David Axmark]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Axmark Context triple: [MySQL AB, notableEmployee, David Axmark]
-
A.
David Axmark
chosen
David Axmark is a Swedish software developer best known as one of the original co-founders and developers of the MySQL relational database management system.
-
B.
Maria Widenius
Maria Widenius is known primarily as the daughter of Finnish software developer Michael "Monty" Widenius, the original creator of the MySQL database.
-
C.
Michael Widenius
Michael Widenius is a Finnish software engineer and entrepreneur best known as the original developer of the MySQL relational database and later the founder of MariaDB.
-
D.
Steve Carlson
Steve Carlson is an American former professional ice hockey player best known for portraying one of the Hanson Brothers in the cult classic film "Slap Shot."
-
E.
Adrian Johansson
Adrian Johansson is the brother of American actress Scarlett Johansson.
- 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_69d889e1030481909950e140c63255b9 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46c474e5481909d2736241b592dab |
completed | April 19, 2026, 5:46 a.m. |
Created at: April 10, 2026, 5:51 a.m.