Triple
T19190911
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rigoletto |
E469832
|
entity |
| Predicate | censoringAuthority |
P77406
|
FINISHED |
| Object | Austrian censors in Venice |
—
|
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: Austrian censors in Venice | Statement: [Rigoletto, censoringAuthority, Austrian censors in Venice]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: censoringAuthority Context triple: [Rigoletto, censoringAuthority, Austrian censors in Venice]
-
A.
censorshipAuthority
chosen
Indicates that one entity has the official power or responsibility to censor, restrict, or approve the information, media, or expression of another entity.
-
B.
censorshipRole
Indicates that an entity has a role or responsibility related to censoring, restricting, or controlling information, media, or expression.
-
C.
censorshipLevel
Indicates the degree or strictness of control, suppression, or restriction applied to information, media, or expression.
-
D.
censorshipReason
Indicates the justification or cause given for why certain content is suppressed, restricted, or removed.
-
E.
censorshipStatusChange
Indicates a change in an entity’s censorship state, such as being newly censored, uncensored, or having its censorship level modified.
- 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_69d8dd0ad9088190a173b32657ae2e7a |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5f8a226dc8190a8a96960a4180298 |
completed | April 20, 2026, 9:57 a.m. |
| PD | Predicate disambiguation | batch_69e4b9bb158481909478ca2e06f3ba39 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:07 p.m.