Triple
T23244291
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hipparcos Catalogue |
E581539
|
entity |
| Predicate | typicalParallaxAccuracy |
P52717
|
FINISHED |
| Object | about 1 milliarcsecond |
—
|
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: about 1 milliarcsecond | Statement: [Hipparcos Catalogue, typicalParallaxAccuracy, about 1 milliarcsecond]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalParallaxAccuracy Context triple: [Hipparcos Catalogue, typicalParallaxAccuracy, about 1 milliarcsecond]
-
A.
parallaxAccuracy
chosen
Indicates the degree of precision or reliability associated with a measured parallax value.
-
B.
parallaxError
Indicates an apparent shift in an object's observed position caused by a change in the observer's viewpoint, leading to measurement inaccuracy.
-
C.
parallax
Indicates the apparent shift in an object’s position relative to a background when observed from two different viewpoints or at two different times.
-
D.
typicalHorizontalAccuracy
Indicates the usual or expected degree of precision in the horizontal (x–y) position of a measurement or location estimate.
-
E.
parallaxZeroPointOffset
Indicates a systematic offset or bias in the reference (zero) point used to measure parallax values.
- 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_69e24606b17c81908aba1a4911c8a8ba |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f193ee37c8819091f799506fa532da |
completed | April 29, 2026, 5:15 a.m. |
| PD | Predicate disambiguation | batch_69effcdadec0819092ec1749ee453b4e |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:10 p.m.