Triple
T11788279
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Latvian Jews |
E280325
|
entity |
| Predicate | percentageKilledInHolocaust |
P44863
|
FINISHED |
| Object | around 90 percent |
—
|
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: around 90 percent | Statement: [Latvian Jews, percentageKilledInHolocaust, around 90 percent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: percentageKilledInHolocaust Context triple: [Latvian Jews, percentageKilledInHolocaust, around 90 percent]
-
A.
percentageOfJewishPopulationKilled
chosen
Indicates the proportion of a Jewish population that was killed, expressed as a percentage of the total.
-
B.
numberOfJewsKilled
Indicates the quantity of Jewish people who were killed in a given event, context, or time period.
-
C.
numberOfJewsDeportedToConcentrationCamps
Indicates the number of Jewish individuals who were forcibly taken and sent to concentration camps.
-
D.
numberOfGermanVictims
Indicates the quantity of victims who are identified as German in the context of the described event or situation.
-
E.
numberOfJewsSaved
Indicates the quantity of Jewish individuals who were rescued or preserved from harm, danger, or persecution in a given context.
- 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_69d6ab258b808190b1735835c841e3a4 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a586803481909af0032c35ca6e51 |
completed | April 10, 2026, 7:23 a.m. |
| PD | Predicate disambiguation | batch_69d8a2491f048190853239bc05090bf4 |
completed | April 10, 2026, 7:10 a.m. |
Created at: April 8, 2026, 9:42 p.m.