Triple
T1621617
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | satoshi |
E35042
|
entity |
| Predicate | introducedWith |
P5655
|
FINISHED |
| Object | Bitcoin protocol |
E5715
|
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: Bitcoin protocol | Statement: [satoshi, introducedWith, Bitcoin protocol]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bitcoin protocol Context triple: [satoshi, introducedWith, Bitcoin protocol]
-
A.
Bitcoin
chosen
Bitcoin is a decentralized digital cryptocurrency that operates without a central bank, enabling peer-to-peer transactions secured by blockchain technology.
-
B.
Bitcoin Core
Bitcoin Core is the open-source software implementation that serves as the primary full node and wallet for the Bitcoin network, maintaining the blockchain and enforcing consensus rules.
-
C.
BitC
BitC is a systems programming language designed for safety, low-level control, and formal verification, drawing on ideas from Modula-3 and capability-based security.
-
D.
satoshi
A satoshi is the smallest divisible unit of the cryptocurrency Bitcoin, representing one hundred millionth of a single bitcoin.
-
E.
Segregated Witness
Segregated Witness is a Bitcoin protocol upgrade that separates signature data from transaction data to increase block capacity, improve scalability, and fix transaction malleability.
- 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_69a886023194819080a3fccd6e325d0e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a909b1fc788190b38c0aa4ccc2e953 |
completed | March 5, 2026, 4:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad71a348788190ae6b8d0b4f10559b |
completed | March 8, 2026, 12:54 p.m. |
Created at: March 4, 2026, 7:28 p.m.