Triple
T37202595
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U.S. Bank Payment Services |
E922079
|
entity |
| Predicate | uses |
P98
|
FINISHED |
| Object |
ACH network
The ACH network is an electronic funds-transfer system in the United States that processes large volumes of batch credit and debit transactions, such as direct deposits, bill payments, and business-to-business payments between bank accounts.
|
E2216820
|
NE 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: ACH network | Statement: [U.S. Bank Payment Services, uses, ACH network]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: ACH network Triple: [U.S. Bank Payment Services, uses, ACH network]
Generated description
The ACH network is an electronic funds-transfer system in the United States that processes large volumes of batch credit and debit transactions, such as direct deposits, bill payments, and business-to-business payments between bank accounts.
Provenance (5 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_69f76ea4849481909b4a3073efb0114c |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb36460fec81908b92cdeb81a5e918 |
completed | May 6, 2026, 12:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a40361d77108190b780b0486ccf80d3 |
completed | June 27, 2026, 8:44 p.m. |
| NEDg | Description generation | batch_6a403692b8c0819080608b791a585931 |
completed | June 27, 2026, 8:46 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a4037016aa881909a72d303ebec4756 |
completed | June 27, 2026, 8:48 p.m. |
Created at: May 3, 2026, 4:15 p.m.