Triple
T8746713
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mbini |
E207846
|
entity |
| Predicate | region |
P40
|
FINISHED |
| Object | Rio Muni |
E281302
|
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: Rio Muni | Statement: [Mbini, region, Rio Muni]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rio Muni Context triple: [Mbini, region, Rio Muni]
-
A.
Rio Muni
chosen
Rio Muni is the mainland region of Equatorial Guinea, located on the west coast of Central Africa and forming the country's largest and most populous territory.
-
B.
Río de Oro
Río de Oro is a river in northeastern Colombia that flows through the Santander region and passes near the city of Bucaramanga.
-
C.
Río de Oro
Río de Oro was a former Spanish colonial territory in northwest Africa that later became part of the disputed region of Western Sahara.
-
D.
Bandama River basin
The Bandama River basin is the largest river drainage system in Côte d'Ivoire, encompassing much of the country's central region and supporting agriculture, settlements, and hydropower.
-
E.
Vallée-du-Ntem
Vallée-du-Ntem is an administrative department in southern Cameroon known for its location along the Ntem River near the border with Gabon and Equatorial Guinea.
- 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_69ca835bb2bc819084bb5906cb6ef7f8 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5d75e7c88190a9e78fadb979e1b6 |
completed | March 31, 2026, 11:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf4313630881909b946cb8a2bdf793 |
completed | April 3, 2026, 4:33 a.m. |
Created at: March 30, 2026, 6:39 p.m.