Triple
T23948580
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mbanza-Ngungu |
E602979
|
entity |
| Predicate | hasNearbyKarstFeature |
P73138
|
FINISHED |
| Object | limestone caves |
—
|
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: limestone caves | Statement: [Mbanza-Ngungu, hasNearbyKarstFeature, limestone caves]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNearbyKarstFeature Context triple: [Mbanza-Ngungu, hasNearbyKarstFeature, limestone caves]
-
A.
karstFeature
Indicates a relationship where a geographic entity is identified as, or associated with, a karst-related landform or feature formed by the dissolution of soluble rocks.
-
B.
isKarstCave
Indicates that a cave is formed primarily through the dissolution of soluble rocks (such as limestone), characterizing it as a karst-type cave.
-
C.
hasNearbyCave
chosen
Indicates that one entity is located close to or in the vicinity of a cave associated with another entity.
-
D.
hasKarstTowerFormations
Indicates that the subject possesses or contains karst tower landforms, typically steep or vertical limestone pillars formed by dissolution and erosion.
-
E.
hasMineralFeature
Indicates that one entity possesses, contains, or is characterized by a specific mineral-related feature or attribute.
- 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_69e2953e4924819093f1c24c03476b42 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1d03067348190a2cccb809ebdc0ad |
completed | April 29, 2026, 9:32 a.m. |
| PD | Predicate disambiguation | batch_69f1615518088190a206f54e2fdb14a3 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:18 p.m.