Triple
T8372019
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pawiak prison |
E197481
|
entity |
| Predicate | primaryVictims |
P36783
|
FINISHED |
| Object | Polish political prisoners |
—
|
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: Polish political prisoners | Statement: [Pawiak prison, primaryVictims, Polish political prisoners]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryVictims Context triple: [Pawiak prison, primaryVictims, Polish political prisoners]
-
A.
victimGroup
Indicates that one group or entity is the target or recipient of harm, abuse, or wrongdoing caused by another.
-
B.
mainVictims
chosen
Indicates that the related entities are the primary or principal targets harmed or affected by an action, event, or perpetrator.
-
C.
coVictim
Indicates that two or more entities are victims in the same harmful event or incident.
-
D.
portraysAsVictim
Indicates that one entity represents or depicts another entity as a victim in a given context or narrative.
-
E.
typeOfVictimization
Indicates the specific kind or category of harmful act, abuse, or exploitation experienced by a victim.
- 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_69ca82f56730819080cec5d991c76f4c |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb80a6944081909c4547688c9e70ae |
completed | March 31, 2026, 8:07 a.m. |
| PD | Predicate disambiguation | batch_69cb70cd04b08190ab5f72afd22a7967 |
completed | March 31, 2026, 6:59 a.m. |
Created at: March 30, 2026, 6:01 p.m.