Triple
T37396154
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barksdale family |
E928858
|
entity |
| Predicate | usesFrontBusiness |
P94881
|
FINISHED |
| Object | Orlando's strip club |
—
|
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: Orlando's strip club | Statement: [Barksdale family, usesFrontBusiness, Orlando's strip club]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesFrontBusiness Context triple: [Barksdale family, usesFrontBusiness, Orlando's strip club]
-
A.
frontBusiness
chosen
Indicates that one entity operates as a façade or cover business for another entity, typically concealing the latter’s true activities or identity.
-
B.
usesBusinessSystem
Indicates that one entity makes use of a particular business system to perform its operations, processes, or functions.
-
C.
usesBusinessModel
Indicates that one entity operates according to, or applies in practice, the business model defined or provided by another entity.
-
D.
hasBusiness
Indicates that one entity owns, operates, or is formally associated with a business entity.
-
E.
supportsBusiness
Indicates that one entity provides assistance, resources, or services that help another entity operate, grow, or succeed in its business activities.
- 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_69f76ebb10c481909b54b9dba263e29f |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb9e1845e881908d19158440cf3b87 |
completed | May 6, 2026, 8:01 p.m. |
| PD | Predicate disambiguation | batch_69fb8d08d6988190a00794ac26078348 |
completed | May 6, 2026, 6:48 p.m. |
Created at: May 3, 2026, 4:16 p.m.