Triple
T2315029
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salé |
E51043
|
entity |
| Predicate | countryCapitalNearby |
P33891
|
FINISHED |
| Object | Rabat |
E8849
|
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: Rabat | Statement: [Salé, countryCapitalNearby, Rabat]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rabat Context triple: [Salé, countryCapitalNearby, Rabat]
-
A.
Rabat
chosen
Rabat is the capital city of Morocco, located on the Atlantic coast and known for its historic medina, coastal fortifications, and role as a political and administrative center.
-
B.
Rabat and Salé
Rabat and Salé are two historically significant, closely linked Moroccan cities on the Atlantic coast, facing each other across the Bou Regreg River.
-
C.
Beni Mellal
Beni Mellal is a major city in central Morocco known for its agricultural importance and its location at the foot of the Middle Atlas mountains.
-
D.
Fès-Meknès
Fès-Meknès is an administrative region in north-central Morocco that includes the historic imperial cities of Fez and Meknès.
-
E.
Marrakesh
Marrakesh is a historic and vibrant city in western Morocco, renowned for its bustling medina, iconic red sandstone architecture, and rich cultural heritage.
- 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_69a88b074b908190ae983dbca7757d88 |
completed | March 4, 2026, 7:41 p.m. |
| NER | Named-entity recognition | batch_69abc61d41f88190983f8947667b4c7a |
completed | March 7, 2026, 6:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b28da24fe88190aabe2bcc520a35dc |
completed | March 12, 2026, 9:55 a.m. |
Created at: March 4, 2026, 7:49 p.m.