Triple
T27638865
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pay-to-Witness-Script-Hash |
E696534
|
entity |
| Predicate | softForkActivation |
P162787
|
FINISHED |
| Object | SegWit 2017 |
—
|
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: SegWit 2017 | Statement: [Pay-to-Witness-Script-Hash, softForkActivation, SegWit 2017]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: softForkActivation Context triple: [Pay-to-Witness-Script-Hash, softForkActivation, SegWit 2017]
-
A.
hardFork
Indicates a protocol change where a blockchain’s rules are modified in a way that is not backward-compatible, causing the chain to split into two divergent versions unless all participants upgrade.
-
B.
hardForkDate
Indicates the date on which a protocol or system undergoes a hard fork, i.e., a non-backward-compatible change that splits or upgrades the network.
-
C.
hardForkReason
Indicates the reason or justification for performing a hard fork in a system or protocol.
-
D.
secondHalvingYear
Indicates the calendar year in which the second halving event of a recurring, typically periodic, process or quantity occurs.
-
E.
supports64bitBlockNumbers
Indicates that the subject is capable of handling or operating with 64-bit block number values.
- F. None of above. chosen
Provenance (4 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_69ef5909f3848190805f35b76833e722 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f6318fec0c8190971b4fc1a7df10d3 |
completed | May 2, 2026, 5:17 p.m. |
| PD | Predicate disambiguation | batch_69f62c1921008190a62675a31f66a875 |
completed | May 2, 2026, 4:53 p.m. |
| PDg | Predicate description generation | batch_69f62d14c24c81909e86678c1b5fd429 |
completed | May 2, 2026, 4:57 p.m. |
Created at: April 27, 2026, 2:25 p.m.