Triple
T8540754
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karura Forest |
E202187
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Gigiri |
E89552
|
NE 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: Gigiri | Statement: [Karura Forest, near, Gigiri]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gigiri Context triple: [Karura Forest, near, Gigiri]
-
A.
Gigiri
chosen
Gigiri is an affluent diplomatic and residential district in Nairobi, Kenya, known for hosting major international institutions and embassies.
-
B.
Meru
Meru is a town in eastern Kenya that serves as a commercial and administrative hub for the surrounding agricultural region near Mount Kenya.
-
C.
Kiliwa
Kiliwa is an indigenous people of northern Baja California, Mexico, known for their distinct Yuman language and traditional hunter-gatherer culture.
-
D.
Mount Ntringui
Mount Ntringui is a volcanic peak on the island of Anjouan in the Comoros, known for its lush forests and prominence in the island’s rugged landscape.
-
E.
Mount Kiematubu
Mount Kiematubu is a volcanic peak that forms the highest point on the Indonesian island of Tidore in the Maluku Islands.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca832461e88190a654c5e44e233aa8 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe6e10bc081909a7210c577b807fb |
completed | March 31, 2026, 3:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cea86036a881909cd1744cdb5b7a7f |
completed | April 2, 2026, 5:33 p.m. |
Created at: March 30, 2026, 6:18 p.m.