Triple
T16080429
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Galkayo |
E390093
|
entity |
| Predicate | roadLinksTo |
P11435
|
FINISHED |
| Object | Bossaso |
E118914
|
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: Bossaso | Statement: [Galkayo, roadLinksTo, Bossaso]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bossaso Context triple: [Galkayo, roadLinksTo, Bossaso]
-
A.
Bossaso
chosen
Bossaso is a major port city in northeastern Somalia that serves as a key commercial and maritime hub on the Gulf of Aden.
-
B.
Obock
Obock is a coastal town in northeastern Djibouti, situated on the Gulf of Tadjoura and known historically as one of the country’s earliest French colonial settlements.
-
C.
Nouadhibou
Nouadhibou is a major coastal city in northwestern Mauritania, known as an important fishing and commercial hub on the Atlantic coast near the Western Sahara border.
-
D.
Dzaoudzi
Dzaoudzi is a coastal town on the island of Petite-Terre in Mayotte, serving as one of the territory’s main urban centers and former capital.
-
E.
Nouakchott
Nouakchott is the capital and largest city of Mauritania, located on the Atlantic coast of Northwest Africa.
- 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_69d86daf32ec8190a8c0466c8f49c3c0 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e21a00f6808190a60939ef7ce727a7 |
completed | April 17, 2026, 11:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffe48adec081909623355eabee472c |
completed | May 10, 2026, 1:51 a.m. |
Created at: April 10, 2026, 4:57 a.m.