Triple
T17272256
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Valley of the Moon |
E419289
|
entity |
| Predicate | hasNightSky |
P84243
|
FINISHED |
| Object | low light pollution |
—
|
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: low light pollution | Statement: [Valley of the Moon, hasNightSky, low light pollution]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNightSky Context triple: [Valley of the Moon, hasNightSky, low light pollution]
-
A.
skyQuality
Indicates the measured level or condition of the sky, typically in terms of clarity, brightness, or suitability for observation.
-
B.
visibleInEveningSky
Indicates that the entity can be seen in the sky during evening hours.
-
C.
isIlluminatedAtNight
Indicates that an entity receives or emits sufficient light to be visibly illuminated during nighttime conditions.
-
D.
hasNightViewSpot
Indicates that a location offers a suitable vantage point for viewing the scenery or cityscape at night.
-
E.
darkSkyRecognition
chosen
Indicates formal recognition that a location meets specific criteria for dark sky quality, such as minimal light pollution and suitability for stargazing or astronomical observation.
- 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_69d886da626481908a14ce7830329a35 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42f4b023c8190b92df4015c14c3a8 |
completed | April 19, 2026, 1:26 a.m. |
| PD | Predicate disambiguation | batch_69e3832c3b98819091967ac7e91ba316 |
completed | April 18, 2026, 1:12 p.m. |
Created at: April 10, 2026, 5:40 a.m.