Triple
T20932351
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Cow |
E515499
|
entity |
| Predicate | censorshipStatusInIran |
P66015
|
FINISHED |
| Object | initially banned then later released |
—
|
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: initially banned then later released | Statement: [The Cow, censorshipStatusInIran, initially banned then later released]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: censorshipStatusInIran Context triple: [The Cow, censorshipStatusInIran, initially banned then later released]
-
A.
censorshipLevel
chosen
Indicates the degree or strictness of control, suppression, or restriction applied to information, media, or expression.
-
B.
censorshipTarget
Indicates that an entity is the object or focus of censorship by another entity or authority.
-
C.
statusInIran
Indicates the legal, social, or political standing or condition of an entity specifically within the context of Iran.
-
D.
censorshipEvent
Indicates an event in which information, expression, or communication is suppressed, restricted, or altered by some controlling authority or mechanism.
-
E.
countryOfCensorshipControversy
Indicates the country in which a particular censorship-related controversy or dispute took place.
- 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_69e0b4fb431c8190b9d40e6a72f0cc87 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6f65681b4819083c7ef6b44ba4bdb |
completed | April 21, 2026, 4 a.m. |
| PD | Predicate disambiguation | batch_69e5c9af1fe08190953366a466950140 |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 12:49 p.m.