Triple
T23258000
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Internet in Sierra Leone |
E581923
|
entity |
| Predicate | mainISPs |
P151566
|
FINISHED |
| Object | Sierratel |
—
|
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: Sierratel | Statement: [Internet in Sierra Leone, mainISPs, Sierratel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sierratel Context triple: [Internet in Sierra Leone, mainISPs, Sierratel]
-
A.
Sierratel
chosen
Sierratel is the state-owned telecommunications company of Sierra Leone, providing fixed-line, mobile, and internet services across the country.
-
B.
Telica
Telica is an active stratovolcano in western Nicaragua known for its frequent eruptions and prominent volcanic crater.
-
C.
Sipa
Sipa is a small settlement located in Rapla County in central Estonia.
-
D.
Giga Bell
Giga Bell is a powerful transformation item in the Super Mario series that turns Mario into a giant, cat-like form capable of battling massive enemies.
-
E.
Telesia
Telesia was an important ancient town in the region of Samnium in south-central Italy, known for its strategic and military significance in pre-Roman and Roman times.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e246079f58819085eaa9c260906880 |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f194c710c48190aff03d210642a043 |
completed | April 29, 2026, 5:19 a.m. |
Created at: April 17, 2026, 4:11 p.m.