Triple
T28045886
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Punkva Caves |
E708677
|
entity |
| Predicate | hasUndergroundRiver |
P165
|
FINISHED |
| Object | Punkva River |
—
|
NE NERFINISHED |
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: Punkva River | Statement: [Punkva Caves, hasUndergroundRiver, Punkva River]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasUndergroundRiver Context triple: [Punkva Caves, hasUndergroundRiver, Punkva River]
-
A.
undergroundRiverLength
Indicates the measured linear extent of an underground river from its starting point to its endpoint.
-
B.
hasUndergroundOrgan
Indicates that an entity possesses an organ or structure that is located below the ground surface.
-
C.
hasRiverBelow
Indicates that one entity is located above another such that a river lies physically below it.
-
D.
hasRiver
chosen
Indicates that a location or area contains, is traversed by, or is directly associated with a river.
-
E.
hasAncestralRiver
Indicates that an entity is associated with or originates from a river regarded as its ancestral or traditional source.
- 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_69ef9b6cf538819094a633ffa67afec1 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca204148190850a3dc325bc07b7 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 27, 2026, 8:29 p.m.