Triple
T30653
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Auschwitz-Birkenau |
E610
|
entity |
| Predicate | hasTypeOfExperiment |
P2119
|
FINISHED |
| Object | medical experiments on prisoners |
—
|
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: medical experiments on prisoners | Statement: [Auschwitz-Birkenau, hasTypeOfExperiment, medical experiments on prisoners]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypeOfExperiment Context triple: [Auschwitz-Birkenau, hasTypeOfExperiment, medical experiments on prisoners]
-
A.
hostsExperiment
Indicates that one entity provides the environment or infrastructure in which another entity’s experiment is conducted or run.
-
B.
hasOperationType
Indicates the specific kind or category of operation associated with an entity or process.
-
C.
hasServiceType
Indicates that an entity is associated with or categorized by a particular type of service.
-
D.
hasExample
Indicates that one entity serves as an instance, illustration, or concrete example of another entity.
-
E.
hasMaterialType
Indicates that something is composed of, made from, or characterized by a specific type of material.
- F. None of above. chosen
Provenance (4 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_69a2479dec388190967ba648663442c9 |
completed | Feb. 28, 2026, 1:40 a.m. |
| NER | Named-entity recognition | batch_69a2490d80a0819083bf604c1229e903 |
completed | Feb. 28, 2026, 1:46 a.m. |
| PD | Predicate disambiguation | batch_69a2486eb01881909241540dda28e1ff |
completed | Feb. 28, 2026, 1:44 a.m. |
| PDg | Predicate description generation | batch_69a2490c9c348190bf8536a08415b94a |
completed | Feb. 28, 2026, 1:46 a.m. |
Created at: Feb. 28, 2026, 1:44 a.m.