Triple
T16267874
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Koosah Falls |
E394917
|
entity |
| Predicate | photographyConditions |
P42052
|
FINISHED |
| Object | best light often in morning or overcast days |
—
|
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: best light often in morning or overcast days | Statement: [Koosah Falls, photographyConditions, best light often in morning or overcast days]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: photographyConditions Context triple: [Koosah Falls, photographyConditions, best light often in morning or overcast days]
-
A.
allowsPhotography
Indicates that one entity permits another entity to take photographs in a particular context or location.
-
B.
hasPhotographyRestrictions
Indicates that there are specific rules or limitations governing whether and how photography is allowed.
-
C.
hasViewingConditions
chosen
Indicates that one entity is associated with specific viewing conditions under which it is meant to be observed or evaluated.
-
D.
hasPhotographicConvention
Indicates that there is an established photographic style, rule, or convention governing how the related entities are visually represented in photographs.
-
E.
usesPhotographyFrom
Indicates that one entity employs or incorporates photographic material originating from 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_69d87f221d8081909b0b2063e7528ba2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e245c963ec8190b059fecac6248cd9 |
completed | April 17, 2026, 2:38 p.m. |
| PD | Predicate disambiguation | batch_69e219f259e88190bf49d8408c04178e |
completed | April 17, 2026, 11:30 a.m. |
Created at: April 10, 2026, 5:05 a.m.