Triple
T3054247
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Łódź Ghetto |
E60440
|
entity |
| Predicate | survivorCountApproximate |
P8803
|
FINISHED |
| Object | about 7000–10000 |
—
|
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: about 7000–10000 | Statement: [Łódź Ghetto, survivorCountApproximate, about 7000–10000]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: survivorCountApproximate Context triple: [Łódź Ghetto, survivorCountApproximate, about 7000–10000]
-
A.
survivorTerm
Indicates that one entity is designated as the surviving or remaining party in relation to another entity, often after a loss, termination, or adverse event.
-
B.
survivorWith
Indicates a relationship where one entity survives an event or condition together with, or in the presence of, another entity.
-
C.
hasSurvivors
Indicates that one or more entities continue to exist or remain alive after a particular event, condition, or incident.
-
D.
estimatedNumberOfPeopleSaved
chosen
Indicates the approximate count of individuals whose lives were preserved or harm was averted as a result of a particular action, intervention, or entity.
-
E.
killedApproximate
Indicates that one entity caused the death of another, but the information about this killing is uncertain, estimated, or not known with exact precision.
- 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_69ad8578137c81908259dcb27c7d6d7c |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ad9bf51b5081908ce355a76cfa9e3c |
completed | March 8, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69ad962195388190856013a2519c2b0f |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 3:01 p.m.