Triple
T29390181
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SDHC |
E745350
|
entity |
| Predicate | physicalDimensions |
P67473
|
FINISHED |
| Object | same as standard SD for full-size cards |
—
|
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: same as standard SD for full-size cards | Statement: [SDHC, physicalDimensions, same as standard SD for full-size cards]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: physicalDimensions Context triple: [SDHC, physicalDimensions, same as standard SD for full-size cards]
-
A.
typicalDimension
chosen
Indicates that one entity represents a standard or characteristic measurement (such as size, length, or capacity) typically associated with another entity.
-
B.
externalDimension
Indicates that an entity has a measurable size or extent along one or more outer spatial dimensions (such as length, width, or height).
-
C.
physicalHeight
Indicates the vertical size or stature of an entity, typically measured as the distance from its base to its highest point.
-
D.
graphicsDimension
Indicates a relationship where an entity has or is associated with a specific graphical size or dimensional properties.
-
E.
typicalDomainDimension
Indicates that a dimension is a standard or characteristic measurement typically associated with a given domain or context.
- 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_69f66d7765208190b87b1cc6d96a151c |
completed | May 2, 2026, 9:32 p.m. |
| PD | Predicate disambiguation | batch_69f66abfdaf08190a55f14c70be6fd4d |
completed | May 2, 2026, 9:21 p.m. |
Created at: April 28, 2026, 2:41 p.m.