Triple
T19436244
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clarity |
E486230
|
entity |
| Predicate | dataRefreshMechanism |
P79875
|
FINISHED |
| Object | ETL from Epic production systems |
—
|
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: ETL from Epic production systems | Statement: [Clarity, dataRefreshMechanism, ETL from Epic production systems]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dataRefreshMechanism Context triple: [Clarity, dataRefreshMechanism, ETL from Epic production systems]
-
A.
dataRefreshLocation
Indicates the place or source from which data is refreshed or updated.
-
B.
refreshType
chosen
Indicates the manner or category of update applied to an entity, such as whether it is a full, partial, or incremental refresh.
-
C.
dataMaintained
Indicates that one entity is responsible for preserving, storing, or keeping another entity’s data up to date and accessible over time.
-
D.
updatedEvery
Indicates that something is refreshed or brought up to date at a regular, specified interval.
-
E.
dataAvailableFrom
Indicates that a specified source or provider offers access to certain data starting from a particular point or under certain conditions.
- 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_69d8e8d7ad488190a3373045029b0f3b |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6336001488190a05f372779711ed2 |
completed | April 20, 2026, 2:08 p.m. |
| PD | Predicate disambiguation | batch_69e4fd6e806081909053f325ba01ab6b |
completed | April 19, 2026, 4:06 p.m. |
Created at: April 10, 2026, 1:38 p.m.