Triple
T29389960
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SD Association |
E745347
|
entity |
| Predicate | setsSpecificationFor |
P8188
|
FINISHED |
| Object | Secure Digital (SD) memory cards |
—
|
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: Secure Digital (SD) memory cards | Statement: [SD Association, setsSpecificationFor, Secure Digital (SD) memory cards]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: setsSpecificationFor Context triple: [SD Association, setsSpecificationFor, Secure Digital (SD) memory cards]
-
A.
hasSpecification
Indicates that an entity is associated with a particular specification that defines or constrains its properties, behavior, or requirements.
-
B.
setsRulesFor
chosen
Indicates that one entity establishes or defines rules, guidelines, or constraints that another entity is expected to follow.
-
C.
specifiedFor
Indicates that something is designated or intended to be used for a particular entity, purpose, or context.
-
D.
setsOn
Indicates that one entity places or arranges another entity onto a specified surface, container, or context.
-
E.
settingOfRule
Indicates the contextual environment, domain, or circumstances within which a particular rule is defined and intended to apply.
- 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_69f0a79dfabc81908755382ee47791e2 |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_69f669d648488190b7d3060432eb0eeb |
completed | May 2, 2026, 9:17 p.m. |
| PD | Predicate disambiguation | batch_69f660f4f7a88190b93c60d76b86c912 |
completed | May 2, 2026, 8:39 p.m. |
Created at: April 28, 2026, 2:41 p.m.