Triple
T28196278
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kast double spectrograph |
E716454
|
entity |
| Predicate | observatoryOperatedBy |
P52706
|
FINISHED |
| Object | University of California Observatories |
—
|
NE NERFINISHED |
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: University of California Observatories | Statement: [Kast double spectrograph, observatoryOperatedBy, University of California Observatories]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: observatoryOperatedBy Context triple: [Kast double spectrograph, observatoryOperatedBy, University of California Observatories]
-
A.
observatoryOrganization
chosen
Indicates that an organization operates, manages, or is institutionally responsible for an observatory.
-
B.
observatoryName
Indicates the name assigned to an observatory.
-
C.
observatoryType
Indicates the specific kind or category of observatory associated with an entity.
-
D.
observatoryFor
Indicates that something serves as an observatory specifically dedicated to observing, studying, or monitoring a particular target or subject.
-
E.
associatedObservatory
Indicates that an entity has a relationship with, or is linked to, a particular observatory, such as being operated by, observed at, or otherwise connected to it.
- 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_69efd6b612f48190a72012b520afbd10 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f6691f5e188190b12c7b2eb729a45e |
completed | May 2, 2026, 9:14 p.m. |
| PD | Predicate disambiguation | batch_69f6659b62fc8190b21555d0ba54db2d |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 27, 2026, 10:28 p.m.