Triple
T25750338
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stardust |
E648454
|
entity |
| Predicate | sampleCollectionMedium |
P159222
|
FINISHED |
| Object | aerogel |
—
|
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: aerogel | Statement: [Stardust, sampleCollectionMedium, aerogel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sampleCollectionMedium Context triple: [Stardust, sampleCollectionMedium, aerogel]
-
A.
sampleCollected
Indicates that a sample has been obtained or gathered from a source as part of a collection process.
-
B.
sampleType
Indicates the classification or category of a sample in relation to a broader set of samples or experimental conditions.
-
C.
usedMedium
Indicates that an action or communication was carried out through a particular medium or channel.
-
D.
collectedWith
Indicates that one entity was gathered, acquired, or obtained together with another entity as part of the same collection event or process.
-
E.
collectedAs
Indicates that one entity has been gathered, acquired, or assembled as part of another entity, such as a collection, set, or group.
- 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_69e7ab314d788190b3abe19e114080e1 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f5fd7df2ac8190a206646c8640cec0 |
completed | May 2, 2026, 1:34 p.m. |
| PD | Predicate disambiguation | batch_69f4938262ac8190b41f922d0407d272 |
completed | May 1, 2026, 11:50 a.m. |
| PDg | Predicate description generation | batch_69f497b8abb88190bb672cf6907c4b8d |
completed | May 1, 2026, 12:08 p.m. |
Created at: April 22, 2026, 4:34 a.m.