Triple
T12665727
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mubadala Capital |
E302547
|
entity |
| Predicate | hasBusinessUnitType |
P7588
|
FINISHED |
| Object | third-party capital management |
—
|
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: third-party capital management | Statement: [Mubadala Capital, hasBusinessUnitType, third-party capital management]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBusinessUnitType Context triple: [Mubadala Capital, hasBusinessUnitType, third-party capital management]
-
A.
hasBusinessTypeAlong
Indicates that a business or commercial entity located along a route, corridor, or area is associated with a specific type or category of business activity.
-
B.
hasTypeOfBusinesses
Indicates that an entity is associated with or contains specific categories or kinds of businesses.
-
C.
hasBusinessDivision
chosen
Indicates that an organization includes or is composed of a specific business division as a subordinate unit.
-
D.
hasKeyBusinessArea
Indicates that an entity is associated with or operates within a particular primary business area or domain.
-
E.
hasTypeOfOrganization
Indicates that an entity is classified as belonging to a particular type or category of organization.
- 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_69d7bded71a88190bb76e2413af9ea66 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9617e030881908444743b8a7e0d75 |
completed | April 10, 2026, 8:45 p.m. |
| PD | Predicate disambiguation | batch_69d960b78ce8819091f15dd5013e6da5 |
completed | April 10, 2026, 8:42 p.m. |
Created at: April 9, 2026, 5:19 p.m.