Triple
T10211985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | OSIRIS-REx |
E242350
|
entity |
| Predicate | sampleCollectionDate |
P65789
|
FINISHED |
| Object | 2020-10-20 |
—
|
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: 2020-10-20 | Statement: [OSIRIS-REx, sampleCollectionDate, 2020-10-20]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sampleCollectionDate Context triple: [OSIRIS-REx, sampleCollectionDate, 2020-10-20]
-
A.
dataCollectedOn
chosen
Indicates that certain data was gathered, recorded, or measured at a specific point in time or on a particular date.
-
B.
startDateOfCollection
Indicates the calendar date on which a particular collection or collecting activity begins.
-
C.
hasCaptureDate
Indicates the date on which something (such as an image, video, or data sample) was originally captured or recorded.
-
D.
accessionDate
Indicates the date on which an item, record, or entity was formally added to a collection, system, or repository.
-
E.
recaptureDate
Indicates the date on which something that was previously captured or held is captured or taken back again.
- 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_69d381ae26c48190985abd0e25ee5d04 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d3aa23bce881909b5deac612ec22cb |
completed | April 6, 2026, 12:42 p.m. |
| PD | Predicate disambiguation | batch_69d39559e5ac8190b88eca75956b7e6a |
completed | April 6, 2026, 11:13 a.m. |
Created at: April 6, 2026, 11:02 a.m.