Triple
T2706253
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fine Guidance Sensor |
E59347
|
entity |
| Predicate | pointingAccuracy |
P9771
|
FINISHED |
| Object | better than 5 milliarcseconds |
—
|
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: better than 5 milliarcseconds | Statement: [Fine Guidance Sensor, pointingAccuracy, better than 5 milliarcseconds]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: pointingAccuracy Context triple: [Fine Guidance Sensor, pointingAccuracy, better than 5 milliarcseconds]
-
A.
interactionPoint
Indicates a specific location or moment where two or more entities come into contact or engage with each other.
-
B.
precision
chosen
Indicates the degree to which an action, measurement, or outcome is carried out with exactness, minimal deviation, and fine-grained accuracy.
-
C.
azimuthAccuracy
Indicates the degree of precision or allowable error in the measured or specified azimuth angle between entities.
-
D.
timekeepingAccuracy
Indicates how closely an entity’s measurement or tracking of time matches the true or standard reference time.
-
E.
positionCoached
Indicates that one entity served as a coach for another entity in a specific position or role.
- 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_69ab4ac66bc88190b9e4afa5fc843f72 |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abda725f24819090e8d936b3d2d5bc |
completed | March 7, 2026, 7:57 a.m. |
| PD | Predicate disambiguation | batch_69abd82062988190b4292f242ad70b2c |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:55 p.m.