Triple
T5127610
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Evan Goldberg |
E115620
|
entity |
| Predicate | founded |
P104
|
FINISHED |
| Object | NetLedger |
E496722
|
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: NetLedger | Statement: [Evan Goldberg, founded, NetLedger]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: NetLedger Context triple: [Evan Goldberg, founded, NetLedger]
-
A.
NetLedger
chosen
NetLedger was an early web-based accounting and business management software company that later evolved into the cloud ERP platform NetSuite.
-
B.
Ledger
Ledger is a surname most famously associated with Australian actor Heath Ledger, known for his acclaimed and influential film performances.
-
C.
Hyperledger
Hyperledger is an open-source collaborative project focused on developing enterprise-grade, permissioned blockchain frameworks and tools for business applications.
-
D.
Algorand blockchain protocol
Algorand blockchain protocol is a scalable, secure, and energy-efficient public blockchain platform designed by cryptographer Silvio Micali that uses a pure proof-of-stake consensus mechanism.
-
E.
Credible Labs
Credible Labs is a U.S.-based online marketplace that allows consumers to compare and refinance loans, including student loans, personal loans, and mortgages.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69bd444426bc819099ccd23f141e22aa |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd782428a081909583c7f368226daf |
completed | March 20, 2026, 4:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69becfd90a848190a1c78063a437cf3c |
completed | March 21, 2026, 5:05 p.m. |
Created at: March 20, 2026, 1:42 p.m.