Triple
T4385810
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wawer massacre |
E99238
|
entity |
| Predicate | victimSelection |
P699
|
FINISHED |
| Object | randomly selected Polish males from Wawer and Anin |
—
|
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: randomly selected Polish males from Wawer and Anin | Statement: [Wawer massacre, victimSelection, randomly selected Polish males from Wawer and Anin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: victimSelection Context triple: [Wawer massacre, victimSelection, randomly selected Polish males from Wawer and Anin]
-
A.
victimParticipation
Indicates that the victim took part in, contributed to, or was otherwise involved in the event or action described.
-
B.
victimGroup
chosen
Indicates that one group or entity is the target or recipient of harm, abuse, or wrongdoing caused by another.
-
C.
coVictim
Indicates that two or more entities are victims in the same harmful event or incident.
-
D.
isVictimOf
Indicates that one entity suffers harm, loss, or wrongdoing as a result of another entity’s actions or events.
-
E.
victimTitle
Indicates that one entity holds a title, role, or designation specifically in the capacity of being a victim in relation to another entity or event.
- 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_69b3454f739481909ff6c28331f0c0b9 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b35264e44c81908dd0e0a81f1353bb |
completed | March 12, 2026, 11:55 p.m. |
| PD | Predicate disambiguation | batch_69b34f572efc8190bad1e5078cbcb75a |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:19 p.m.