Triple
T22187972
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ibrahim ibn al-Aghlab |
E548343
|
entity |
| Predicate | title |
P38
|
FINISHED |
| Object | Emir |
—
|
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: Emir | Statement: [Ibrahim ibn al-Aghlab, title, Emir]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Emir Context triple: [Ibrahim ibn al-Aghlab, title, Emir]
-
A.
Emir of Gumel
The Emir of Gumel is the traditional monarch and cultural leader of the historic Gumel emirate in northern Nigeria.
-
B.
Emir of Daura
The Emir of Daura is the hereditary monarch and spiritual-traditional leader of the historic Daura emirate in northern Nigeria, regarded as one of the oldest Hausa royal institutions.
-
C.
Emir of Kazaure
The Emir of Kazaure is the traditional monarch and highest-ranking hereditary ruler of the Kazaure Emirate in northern Nigeria.
-
D.
Califa
Califa is an alternative transliteration of the Arabic title "Khalifa," commonly referring to a caliph or Islamic leader.
-
E.
Emirs
chosen
Emirs are traditional Muslim rulers or leaders, particularly in parts of West Africa and the Middle East, who hold significant religious, cultural, and sometimes political authority within their communities.
- 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_69e11e3e0c7c8190b30d278845e2497e |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12aaa32288190830f6dfc626fb26a |
completed | April 28, 2026, 9:46 p.m. |
Created at: April 16, 2026, 8:35 p.m.