Triple
T18775909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sobieski’s Shield |
E459132
|
entity |
| Predicate | relativeBrightness |
P55247
|
FINISHED |
| Object | faint constellation |
—
|
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: faint constellation | Statement: [Sobieski’s Shield, relativeBrightness, faint constellation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relativeBrightness Context triple: [Sobieski’s Shield, relativeBrightness, faint constellation]
-
A.
relativeLuminance
chosen
Indicates the measured brightness of one entity relative to a reference or to other entities in the same context.
-
B.
surfaceBrightnessClass
Indicates the qualitative classification of how bright an extended object (such as a galaxy) appears per unit area on the sky.
-
C.
apparentBrightness
Indicates how bright one object appears from the perspective or location of another, regardless of its actual intrinsic luminosity.
-
D.
intrinsicBrightness
Indicates the inherent level of light or luminosity an entity possesses, independent of external factors or observation conditions.
-
E.
rayBrightness
Indicates the intensity or luminance level associated with a specific ray.
- 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_69d8d395dba0819087568404508590cb |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5933ad4288190b17e5fad57d8417d |
completed | April 20, 2026, 2:45 a.m. |
| PD | Predicate disambiguation | batch_69e48d1126e4819099607837ed5aadca |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:52 a.m.