Triple
T23182903
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Block, Inc. |
E579507
|
entity |
| Predicate | hasSubsidiary |
P254
|
FINISHED |
| Object | Cash App |
—
|
NE NERFINISHED |
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: Cash App | Statement: [Block, Inc., hasSubsidiary, Cash App]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cash App Context triple: [Block, Inc., hasSubsidiary, Cash App]
-
A.
Cash App
chosen
Cash App is a popular mobile payment and financial services platform that lets users send and receive money, manage a balance, invest in stocks and Bitcoin, and use a linked debit card.
-
B.
Cash App Card
Cash App Card is a customizable Visa debit card linked to a user's Cash App balance, enabling in-store and online purchases as well as ATM withdrawals.
-
C.
Apple Cash
Apple Cash is a digital peer-to-peer payment service by Apple that lets users send, receive, and store money on their Apple devices for use in apps, online, and in stores.
-
D.
Venmo
Venmo is a popular U.S.-based mobile payment service that lets users quickly send, receive, and share money with others, often with a social feed component.
-
E.
Paypay
Paypay is a coastal barangay in the municipality of Daanbantayan in Cebu, Philippines.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245ff8000819090d12008805315b7 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18f705c14819082c8580a03ed6286 |
completed | April 29, 2026, 4:56 a.m. |
Created at: April 17, 2026, 4:05 p.m.