Triple
T33566933
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GRS80 |
E859784
|
entity |
| Predicate | referenceFrameUsage |
P124922
|
FINISHED |
| Object | global geodesy |
—
|
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: global geodesy | Statement: [GRS80, referenceFrameUsage, global geodesy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: referenceFrameUsage Context triple: [GRS80, referenceFrameUsage, global geodesy]
-
A.
usedReferenceFrame
Indicates that one entity adopts or relies on another entity as the coordinate system or reference frame for describing positions, motions, or measurements.
-
B.
usesFrame
chosen
Indicates that one entity employs, relies on, or is structured around a particular frame, framework, or reference structure provided by another entity.
-
C.
frameDependent
Indicates that the truth or interpretation of the relationship depends on the particular reference frame, context, or perspective from which it is evaluated.
-
D.
referenceState
Indicates that one entity serves as a reference or baseline state against which another entity’s state is defined, compared, or interpreted.
-
E.
usesReferenceObjects
Indicates that an entity performs an action or makes a determination by relying on one or more other entities as reference points or benchmarks.
- 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_69f3497c1d288190a844ea699914e038 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fde9fc184c8190bebef35df0e76076 |
completed | May 8, 2026, 1:49 p.m. |
| PD | Predicate disambiguation | batch_69fde6e5beb4819094945a695e961d88 |
completed | May 8, 2026, 1:36 p.m. |
Created at: May 1, 2026, 1:40 a.m.