Triple
T539963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Strasbourg |
E12607
|
entity |
| Predicate | twinCity |
P1072
|
FINISHED |
| Object | Dakar |
E13945
|
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: Dakar | Statement: [Strasbourg, twinCity, Dakar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dakar Context triple: [Strasbourg, twinCity, Dakar]
-
A.
Dakar
chosen
Dakar is the capital and largest city of Senegal, located on the Atlantic coast and serving as a major political, economic, and cultural hub of West Africa.
-
B.
Nouakchott
Nouakchott is the capital and largest city of Mauritania, located on the Atlantic coast of Northwest Africa.
-
C.
Libreville
Libreville is the largest city and main economic and cultural center of Gabon, located on the country’s Atlantic coast.
-
D.
Tadjoura
Tadjoura is a historic coastal town in Djibouti on the Gulf of Tadjoura, known as one of the country’s oldest settlements and a traditional trading hub.
-
E.
Algiers
Algiers is the capital and largest city of Algeria, a major political, economic, and cultural center on the Mediterranean coast of North 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_69a49334226c81908b0ea1689ef6aa3f |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4985e51908190a34aa82ea9dbee1e |
completed | March 1, 2026, 7:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a4c671eaac8190a4bc731a02a5b0e8 |
completed | March 1, 2026, 11:06 p.m. |
Created at: March 1, 2026, 7:32 p.m.