Triple
T25642912
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bezos Day One Fund |
E642879
|
entity |
| Predicate | commitmentAmount |
P101256
|
FINISHED |
| Object | 2000000000 USD |
—
|
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: 2000000000 USD | Statement: [Bezos Day One Fund, commitmentAmount, 2000000000 USD]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commitmentAmount Context triple: [Bezos Day One Fund, commitmentAmount, 2000000000 USD]
-
A.
fundingCommitment
chosen
Indicates a promise or obligation by one party to provide a specified amount or type of funding to another party or project.
-
B.
authorizedBondAmount
Indicates the maximum bond value that has been formally approved or permitted for issuance or use in a given context.
-
C.
guaranteeCommitments
Indicates a relationship where one party formally assures that specific obligations or promises made to another party will be fulfilled or upheld.
-
D.
coreCommitment
Indicates a fundamental, central obligation or promise that defines the primary responsibility or dedication within a relationship or agreement.
-
E.
amountDependsOn
Indicates that the quantity or magnitude of one entity is determined by, or varies as a function of, another entity.
- 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_69e77e7ce28081908b08d65ee6e5c8be |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f6352fdb788190b9bad30243690743 |
completed | May 2, 2026, 5:32 p.m. |
| PD | Predicate disambiguation | batch_69f63182f1408190bddc1214fcbd6145 |
completed | May 2, 2026, 5:16 p.m. |
Created at: April 21, 2026, 5:46 p.m.