Triple
T2734754
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alexander Pechersky |
E60601
|
entity |
| Predicate | aimOfActivity |
P8834
|
FINISHED |
| Object | mass escape of prisoners from Sobibor |
—
|
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: mass escape of prisoners from Sobibor | Statement: [Alexander Pechersky, aimOfActivity, mass escape of prisoners from Sobibor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: aimOfActivity Context triple: [Alexander Pechersky, aimOfActivity, mass escape of prisoners from Sobibor]
-
A.
targetedActivity
Indicates that an activity is specifically directed or focused toward a particular entity, group, or objective.
-
B.
activity
Indicates that an entity is engaged in or performing a particular action, behavior, or process.
-
C.
activityType
chosen
Indicates the specific kind or category of action or event that an entity is engaged in or associated with.
-
D.
settingOfActivities
Indicates that a particular place or context serves as the environment in which certain activities occur or are carried out.
-
E.
majorActivity
Indicates that the related entity performs, participates in, or is primarily associated with a main or most significant activity.
- 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_69ab4b77febc819095603eb012cd141b |
completed | March 6, 2026, 9:47 p.m. |
| NER | Named-entity recognition | batch_69abdb1022488190af84e536946b2e37 |
completed | March 7, 2026, 8 a.m. |
| PD | Predicate disambiguation | batch_69abd82859348190bce3be8f2e9d60ba |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:56 p.m.