Triple
T32201232
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stalingrad prisoner-of-war camp |
E822541
|
entity |
| Predicate | hasPrisonerOrigin |
P45939
|
FINISHED |
| Object | Battle of Stalingrad |
—
|
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: Battle of Stalingrad | Statement: [Stalingrad prisoner-of-war camp, hasPrisonerOrigin, Battle of Stalingrad]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrisonerOrigin Context triple: [Stalingrad prisoner-of-war camp, hasPrisonerOrigin, Battle of Stalingrad]
-
A.
prisonerOrigin
chosen
Indicates that a prisoner comes from, or is originally associated with, a specified place or source.
-
B.
hasInmateOrigin
Indicates that an inmate originates from, or is associated with, a particular source, location, or institution.
-
C.
hasPerpetratorOrigin
Indicates that the origin or source of a perpetrator (such as their nationality, place of birth, or background) is associated with a particular event, action, or crime.
-
D.
hasPrisonerNationality
Indicates that a prisoner is associated with a specific nationality.
-
E.
hasPrison
Indicates that one entity possesses, contains, or is the location of a prison associated with another entity.
- 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_69f349093174819086e633c190a51aa8 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a00b34364448190b8c9948d5a24d845 |
completed | May 10, 2026, 4:33 p.m. |
| PD | Predicate disambiguation | batch_6a00b2e4f13c819081bac7d763c414ad |
completed | May 10, 2026, 4:31 p.m. |
Created at: May 1, 2026, 12:36 a.m.