Triple
T34678078
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Democratic Party of Slovakia |
E890544
|
entity |
| Predicate | wasMarginalizedBy |
P159323
|
FINISHED |
| Object | Communist Party of Slovakia |
—
|
NE NERFINISHED |
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: Communist Party of Slovakia | Statement: [Democratic Party of Slovakia, wasMarginalizedBy, Communist Party of Slovakia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasMarginalizedBy Context triple: [Democratic Party of Slovakia, wasMarginalizedBy, Communist Party of Slovakia]
-
A.
marginalizes
chosen
Indicates treating an individual or group as insignificant or peripheral, limiting their power, voice, or participation within a larger social, political, or organizational context.
-
B.
hasHistoricMarginality
Indicates that an entity has experienced historical social, economic, or political marginalization relative to dominant groups.
-
C.
wasMarkedBy
Indicates that an entity bears a mark, sign, or indication that was applied or caused by another entity.
-
D.
causeOfMarginalization
Indicates a factor, action, or condition that contributes to the social, economic, or political marginalization of an entity.
-
E.
discriminatedAgainst
Indicates that one entity treats another unfairly or unequally based on a particular characteristic, such as race, gender, or other protected attributes.
- 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_69f349dabc008190a18999c26682ed47 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f72325f5b081909fe6821ea2fef16b |
completed | May 3, 2026, 10:27 a.m. |
| PD | Predicate disambiguation | batch_69f72157af108190880317a62e634bb0 |
completed | May 3, 2026, 10:20 a.m. |
Created at: May 1, 2026, 2:05 a.m.