Triple
T35685977
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Petlice samizdat series |
E1031147
|
entity |
| Predicate | riskForParticipants |
P147863
|
FINISHED |
| Object | political persecution |
—
|
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: political persecution | Statement: [Petlice samizdat series, riskForParticipants, political persecution]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: riskForParticipants Context triple: [Petlice samizdat series, riskForParticipants, political persecution]
-
A.
riskToMembers
chosen
Indicates that something poses a potential danger, harm, or adverse impact to the members of a group or organization.
-
B.
riskToUser
Indicates that something poses a potential danger, harm, or adverse impact to the user.
-
C.
riskToSpeaker
Indicates that the action, event, or situation poses a potential danger, harm, or adverse consequence to the speaker.
-
D.
riskTakenFor
Indicates that one entity accepts or undertakes a risk for the benefit, protection, or sake of another entity.
-
E.
riskOfMembership
Indicates that there is a potential or likelihood that an entity will become a member of a particular group or category.
- 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_69f76e0bb6608190ad3a1880be54a17d |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7a01fadac8190a429777cec614eca |
completed | May 3, 2026, 7:21 p.m. |
| PD | Predicate disambiguation | batch_69f79e4d885881908a3612e2e75cf84f |
completed | May 3, 2026, 7:13 p.m. |
Created at: May 3, 2026, 4:05 p.m.