Triple
T15456288
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mid-Scale Observatories program |
E371776
|
entity |
| Predicate | scaleRelativeTo |
P57293
|
FINISHED |
| Object | larger than small telescopes |
—
|
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: larger than small telescopes | Statement: [Mid-Scale Observatories program, scaleRelativeTo, larger than small telescopes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scaleRelativeTo Context triple: [Mid-Scale Observatories program, scaleRelativeTo, larger than small telescopes]
-
A.
scaleProperty
Indicates that one entity defines or modifies the scale, magnitude, or proportional sizing used to interpret or represent a property of another entity.
-
B.
scalePosition
Indicates the relative location or index of an element within a defined scale or ordered measurement framework.
-
C.
similarScaleTo
chosen
Indicates that two entities have comparable magnitude, size, or extent along a given dimension or measurement scale.
-
D.
scalingProperty
Indicates how a quantity or behavior changes in proportion to changes in another variable, typically under resizing or rescaling conditions.
-
E.
scaleOptimizedFor
Indicates that something has been adjusted or configured to operate most efficiently at a particular size, level, or magnitude.
- 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_69d85cc8bd308190886949510b42e764 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03f146a2c8190882741af3ec15268 |
completed | April 16, 2026, 1:44 a.m. |
| PD | Predicate disambiguation | batch_69ded28276f481908c2038bb301e57cf |
completed | April 14, 2026, 11:49 p.m. |
Created at: April 10, 2026, 3:31 a.m.