Triple
T28900204
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DIN 41612 |
E732931
|
entity |
| Predicate | hasRetentionFeature |
P200543
|
FINISHED |
| Object | latching hardware options |
—
|
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: latching hardware options | Statement: [DIN 41612, hasRetentionFeature, latching hardware options]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRetentionFeature Context triple: [DIN 41612, hasRetentionFeature, latching hardware options]
-
A.
hasRetentionModuleCompatibility
Indicates that one entity is compatible with, or can properly operate using, a specified retention module.
-
B.
retentionMethod
Indicates the method or strategy used to retain or keep something (such as data, customers, or resources) over time.
-
C.
canRetain
Indicates that one entity has the ability or permission to keep, hold, or maintain possession or control of another entity over time.
-
D.
performanceRetention
Indicates how well a previously achieved level of performance is maintained over time or across repeated instances.
-
E.
designedToRetain
Indicates that something has been intentionally created or configured for the purpose of holding, keeping, or maintaining another thing in place or in possession.
- F. None of above. chosen
Provenance (4 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_69f05b08c2008190ac426a035a2ed66d |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69ff956dc6548190979171d4b4068d47 |
completed | May 9, 2026, 8:13 p.m. |
| PD | Predicate disambiguation | batch_69ff93dc39c481908a97a12c3ef7dfe7 |
completed | May 9, 2026, 8:06 p.m. |
| PDg | Predicate description generation | batch_69ff956cd640819081efc31f313690b0 |
completed | May 9, 2026, 8:13 p.m. |
Created at: April 28, 2026, 8:02 a.m.