Triple
T4600045
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Axmark |
E100300
|
entity |
| Predicate | softwareTypeWorkedOn |
P38664
|
FINISHED |
| Object | relational database management system |
—
|
LITERAL 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: relational database management system | Statement: [David Axmark, softwareTypeWorkedOn, relational database management system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: softwareTypeWorkedOn Context triple: [David Axmark, softwareTypeWorkedOn, relational database management system]
-
A.
productTypeWorkedOn
chosen
Indicates that an entity has worked on or been involved in creating, developing, or handling a particular type of product.
-
B.
worksOnProgram
Indicates that an entity is actively involved in contributing effort or performing tasks on a particular program.
-
C.
developedWith
Indicates that something was created, built, or produced using a specified tool, technology, method, or collaborator.
-
D.
programUsed
Indicates that a particular program, software, or application was employed or utilized in performing an action or achieving a result.
-
E.
softwareExperience
Indicates the level or extent of a person's prior experience working with or using specific software.
- F. None of above.
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_69bd43cbc014819098b45f435908f88a |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd5971f448819090f6e76c7d3ffc2d |
completed | March 20, 2026, 2:28 p.m. |
| PD | Predicate disambiguation | batch_69bd522c811c81909aae4feadae33174 |
completed | March 20, 2026, 1:57 p.m. |
Created at: March 20, 2026, 1:11 p.m.