Triple
T19585820
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Warburg Pincus |
E490101
|
entity |
| Predicate | AUM |
P136359
|
FINISHED |
| Object | over 80 billion US dollars |
—
|
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: over 80 billion US dollars | Statement: [Warburg Pincus, AUM, over 80 billion US dollars]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: AUM Context triple: [Warburg Pincus, AUM, over 80 billion US dollars]
-
A.
éA
Indicates a directed association or influence from one entity toward another, where the first entity acts upon, affects, or is related to the second in a specified manner.
-
B.
Armisen
Indicates a relationship or action involving someone named Armisen, such as participation, authorship, or association, depending on the specific context in which the predicate is used.
-
C.
أُلغي
Indicates that an action, event, or arrangement has been canceled or annulled.
-
D.
الأم
Indicates a maternal relationship where one entity is the mother of another entity.
-
E.
eon
Indicates a very long, often immeasurable or indefinitely extended, span of time between entities or events.
- 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_69d8e8dd9374819098e36349b3211663 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e640513134819082cf233fa3dcc911 |
completed | April 20, 2026, 3:03 p.m. |
| PD | Predicate disambiguation | batch_69e514dbdb988190b55931a8138c73e7 |
completed | April 19, 2026, 5:46 p.m. |
| PDg | Predicate description generation | batch_69e5174b060c81908937ff9ff7fce611 |
completed | April 19, 2026, 5:56 p.m. |
Created at: April 10, 2026, 1:42 p.m.