Triple
T4254860
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | August Marks |
E95947
|
entity |
| Predicate | usesCoverBusiness |
P33645
|
FINISHED |
| Object | legitimate real estate ventures |
—
|
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: legitimate real estate ventures | Statement: [August Marks, usesCoverBusiness, legitimate real estate ventures]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesCoverBusiness Context triple: [August Marks, usesCoverBusiness, legitimate real estate ventures]
-
A.
usesCoverOrganizations
chosen
Indicates that an entity operates through or makes use of front or intermediary organizations to conceal its true identity, role, or activities.
-
B.
typicallyCovers
Indicates that one entity is the kind of thing that usually or normally includes, addresses, or encompasses another entity.
-
C.
usesBusinessModel
Indicates that one entity operates according to, or applies in practice, the business model defined or provided by another entity.
-
D.
mayCover
Indicates that one entity is permitted or able to extend over, include, or provide coverage for another entity, either partially or fully.
-
E.
usesBusinessSystem
Indicates that one entity makes use of a particular business system to perform its operations, processes, or functions.
- 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_69b3453f759881909b91f01a1e82c036 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34ec036e8819087d8585170707545 |
completed | March 12, 2026, 11:39 p.m. |
| PD | Predicate disambiguation | batch_69b347f73e008190a908a48ef389945a |
completed | March 12, 2026, 11:10 p.m. |
Created at: March 12, 2026, 11:06 p.m.