Triple
T18655635
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | uKhahlamba |
E456057
|
entity |
| Predicate | hasRockArtTradition |
P62930
|
FINISHED |
| Object | San rock paintings |
—
|
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: San rock paintings | Statement: [uKhahlamba, hasRockArtTradition, San rock paintings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRockArtTradition Context triple: [uKhahlamba, hasRockArtTradition, San rock paintings]
-
A.
hasRockArtSite
Indicates that an entity possesses, contains, or is associated with a rock art site.
-
B.
hasRockArtSubject
chosen
Indicates that something features or is associated with a particular subject depicted in rock art.
-
C.
hasRockCarvingsFrom
Indicates that something contains or features rock carvings that originate from a specified source, place, or period.
-
D.
numberOfRockArtSites
Indicates the count of rock art sites associated with a given subject or context.
-
E.
hasArchaeologicalCulture
Indicates that an entity is associated with, belongs to, or is characterized by a particular archaeological culture.
- 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_69d8d38ea1e88190997e9b231190ba6f |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e55084012881909b9dd60565011c86 |
completed | April 19, 2026, 10 p.m. |
| PD | Predicate disambiguation | batch_69e478d85864819093cbad5ed9b54878 |
completed | April 19, 2026, 6:40 a.m. |
Created at: April 10, 2026, 11:47 a.m.