Triple
T23944444
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Minnesota Mining and Manufacturing Company |
E602875
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | conglomerate company |
C15000
|
CONCEPT FINISHED |
How this triple was built (1 step)
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.
CD
Concept disambiguation
gpt-5-mini-2025-08-07
Target class: conglomerate company Context triple: [Minnesota Mining and Manufacturing Company, instanceOf, conglomerate company]
-
A.
Conglomerate
chosen
A conglomerate is a large corporation composed of diverse, often unrelated businesses or subsidiaries managed under a single corporate group.
-
B.
industrial holding company
An industrial holding company is a parent corporation that owns controlling interests in multiple industrial or manufacturing businesses, managing them strategically while typically leaving day-to-day operations to subsidiary management.
-
C.
business holding company
A business holding company is a legal entity that owns controlling interests in other companies’ shares or assets, primarily to manage, oversee, and coordinate their operations and strategic direction without directly producing goods or services itself.
-
D.
multinational consortium
A multinational consortium is a collaborative alliance of independent organizations from multiple countries that pool resources, expertise, and risks to pursue shared objectives or large-scale projects.
-
E.
multinational technology conglomerate
A multinational technology conglomerate is a large corporation that operates across multiple countries and industries, owning and managing diverse technology-focused businesses under a unified corporate structure.
- F. None of above.
Provenance (1 batch)
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_69e2953e4924819093f1c24c03476b42 |
completed | April 17, 2026, 8:17 p.m. |
Created at: April 17, 2026, 9:11 p.m.