Triple
T9339087
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Edictum Rothari |
E224718
|
entity |
| Predicate | legalAudience |
P10804
|
FINISHED |
| Object | Lombard subjects |
—
|
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: Lombard subjects | Statement: [Edictum Rothari, legalAudience, Lombard subjects]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: legalAudience Context triple: [Edictum Rothari, legalAudience, Lombard subjects]
-
A.
regulatoryAudience
Indicates that something is intended for, directed toward, or relevant to a regulatory body or oversight authority as its audience.
-
B.
legalSubject
Indicates that an entity is the bearer of legal rights, duties, or responsibilities within a legal relationship or context.
-
C.
typicalAudience
chosen
Indicates the group of people for whom something (such as a work, product, or resource) is primarily intended or most suitable.
-
D.
legalScope
Indicates the range, boundaries, or extent of authority, applicability, or effect that something has under a particular legal framework or rule.
-
E.
relatesToAudience
Indicates a general relationship or relevance between something and a particular audience or group of recipients.
- 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_69ca84286fcc81909f6e7fd7a7e862a2 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd4bace8488190a18c54e03be8410c |
completed | April 1, 2026, 4:45 p.m. |
| PD | Predicate disambiguation | batch_69cc7a66aef08190b8d668cff5b04f5f |
completed | April 1, 2026, 1:52 a.m. |
Created at: March 30, 2026, 7:40 p.m.