Triple
T22722987
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hannover Unified Biobank |
E561913
|
entity |
| Predicate | typeOfSamples |
P67742
|
FINISHED |
| Object | human samples |
—
|
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: human samples | Statement: [Hannover Unified Biobank, typeOfSamples, human samples]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfSamples Context triple: [Hannover Unified Biobank, typeOfSamples, human samples]
-
A.
sampleType
chosen
Indicates the classification or category of a sample in relation to a broader set of samples or experimental conditions.
-
B.
samplingType
Indicates the method or strategy used to select samples from a larger set or population.
-
C.
typeOfSets
Indicates that one entity specifies or classifies the kind or category of sets to which another entity belongs.
-
D.
featuresSamplesFrom
Indicates that one entity includes or incorporates sample elements originating from another entity.
-
E.
basedOnSampleOf
Indicates that something is derived, inferred, or constructed from a particular sample or subset of data rather than from the entire population.
- 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_69e2454fc984819088213b58ee87a002 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f17927e0348190a4dba430563ef155 |
completed | April 29, 2026, 3:21 a.m. |
| PD | Predicate disambiguation | batch_69eed2a971c0819088af574e40c9343f |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:20 p.m.