Triple
T25750392
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Genesis |
E648455
|
entity |
| Predicate | sampleCollectorType |
P159222
|
FINISHED |
| Object | ultra-pure collector arrays |
—
|
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: ultra-pure collector arrays | Statement: [Genesis, sampleCollectorType, ultra-pure collector arrays]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sampleCollectorType Context triple: [Genesis, sampleCollectorType, ultra-pure collector arrays]
-
A.
sampleType
Indicates the classification or category of a sample in relation to a broader set of samples or experimental conditions.
-
B.
sampleCollected
Indicates that a sample has been obtained or gathered from a source as part of a collection process.
-
C.
samplingType
Indicates the method or strategy used to select samples from a larger set or population.
-
D.
sampleCollectionMedium
chosen
Indicates the physical medium, material, or device used to collect or hold a sample during the sampling process.
-
E.
dataTypeCollected
Indicates that a specific type or category of data is gathered or recorded in the context of an entity or process.
- 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_69e7ab314d788190b3abe19e114080e1 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f621fcea1481909b6f8b3af1ee6820 |
completed | May 2, 2026, 4:10 p.m. |
| PD | Predicate disambiguation | batch_69f620dc38088190b56b2b15ed75b3c2 |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 22, 2026, 4:34 a.m.