Triple
T1115799
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Angel Falls |
E11096
|
entity |
| Predicate | sprayVisibility |
P9694
|
FINISHED |
| Object | visible from great distance |
—
|
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: visible from great distance | Statement: [Angel Falls, sprayVisibility, visible from great distance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sprayVisibility Context triple: [Angel Falls, sprayVisibility, visible from great distance]
-
A.
hasSpray
Indicates that one entity possesses, contains, or is equipped with a spray or spraying capability in relation to another entity or context.
-
B.
visibleAt
chosen
Indicates that one entity can be seen or perceived from a specific location, viewpoint, or context at a given time.
-
C.
gainedVisibilityThrough
Indicates that one entity became more visible, prominent, or well-known as a result of another entity or mechanism.
-
D.
canBeSeenWith
Indicates that two entities are observable together in the same context, setting, or time.
-
E.
visibilityDuration
Indicates the length of time for which something remains visible or observable.
- 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_69a493252a648190ac48f8742474a5e8 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4bbd92a8c8190a16e55f3f739010f |
completed | March 1, 2026, 10:21 p.m. |
| PD | Predicate disambiguation | batch_69a4bb42990c819080db96478fd4977e |
completed | March 1, 2026, 10:18 p.m. |
Created at: March 1, 2026, 7:43 p.m.