Triple
T29924449
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Media in Eritrea |
E760039
|
entity |
| Predicate | journalistSafety |
P20293
|
FINISHED |
| Object | high risk of imprisonment |
—
|
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: high risk of imprisonment | Statement: [Media in Eritrea, journalistSafety, high risk of imprisonment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: journalistSafety Context triple: [Media in Eritrea, journalistSafety, high risk of imprisonment]
-
A.
journalistsFace
chosen
Indicates that journalists encounter or experience a particular challenge, condition, or situation.
-
B.
humanRightsSituation
Indicates the overall condition, treatment, and respect for individuals’ fundamental rights and freedoms within a given context or jurisdiction.
-
C.
journalismType
Indicates the specific category or style of journalism that characterizes a given journalistic work or activity.
-
D.
JamesBradyInjuryContext
Indicates a contextual relationship in which James Brady’s injury is relevant, framing events, actions, or circumstances in terms of that injury.
-
E.
civilLibertiesPolicy
Indicates a policy stance or action concerning the protection, restriction, or regulation of individuals’ civil liberties.
- 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_69f224631674819080c8d089674f9f4f |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f67795fdd4819088f3c7d0de598699 |
completed | May 2, 2026, 10:15 p.m. |
| PD | Predicate disambiguation | batch_69f66ec8298c8190b41fe9d182c05676 |
completed | May 2, 2026, 9:38 p.m. |
Created at: April 29, 2026, 6:15 p.m.