Triple
T7899191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Segregated Witness |
E183405
|
entity |
| Predicate | addsField |
P33246
|
FINISHED |
| Object | witness data to transactions |
—
|
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: witness data to transactions | Statement: [Segregated Witness, addsField, witness data to transactions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: addsField Context triple: [Segregated Witness, addsField, witness data to transactions]
-
A.
definesField
chosen
Indicates that one entity specifies or declares a particular field or attribute that belongs to or characterizes another entity.
-
B.
generatesField
Indicates that one entity produces or gives rise to a particular field associated with another entity.
-
C.
supportsField
Indicates that one entity provides the necessary structure, stability, or backing for a particular field, area, or domain associated with another entity.
-
D.
fromField
Indicates that something originates in, is sourced from, or is associated with a particular field or domain.
-
E.
namedAfterField
Indicates that one entity has been given a name derived from or in honor of another entity, typically a person, place, or thing.
- F. None of above.
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_69ca828d13088190b222be7aa9f9315c |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3a2ae5048190a6824d34b582c366 |
completed | March 31, 2026, 3:06 a.m. |
| PD | Predicate disambiguation | batch_69cae92d94448190b4425bbfb64c658c |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 5:01 p.m.