Triple
T19117678
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UGC 6549 |
E467947
|
entity |
| Predicate | hasLowerLuminosityThan |
P70711
|
FINISHED |
| Object | large spiral galaxies |
—
|
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: large spiral galaxies | Statement: [UGC 6549, hasLowerLuminosityThan, large spiral galaxies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLowerLuminosityThan Context triple: [UGC 6549, hasLowerLuminosityThan, large spiral galaxies]
-
A.
hasLowLuminosity
Indicates that an entity emits relatively little light or energy compared to a typical or reference level.
-
B.
hasVeryLowSurfaceBrightness
Indicates that an entity exhibits an extremely faint or low level of brightness across its visible surface.
-
C.
hasLowerOpticalDepthThan
Indicates that one entity exhibits a smaller (more transparent) optical depth than another entity, meaning it allows more radiation to pass through.
-
D.
hasNoStarBrighterThanMagnitude
Indicates that, within a given set or system, there is no star whose brightness exceeds (is numerically less than) the specified magnitude threshold.
-
E.
isFainterThan
chosen
Indicates that one entity emits less light or appears less bright in comparison to another entity.
- 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_69d8dd06a26481908039e2a1bae8c597 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e399a6d8819090a9501ff1637b9d |
completed | April 20, 2026, 8:28 a.m. |
| PD | Predicate disambiguation | batch_69e4b9b085288190b974d649e12e0844 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 12:05 p.m.