Triple
T21573894
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | al-Māzarī |
E532348
|
entity |
| Predicate | placeOfActivity |
P1527
|
FINISHED |
| Object | Ifriqiya |
—
|
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: Ifriqiya | Statement: [al-Māzarī, placeOfActivity, Ifriqiya]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ifriqiya Context triple: [al-Māzarī, placeOfActivity, Ifriqiya]
-
A.
Maghrib
Maghrib is the Islamic sunset prayer, one of the five daily obligatory prayers in Islam.
-
B.
North Africa
chosen
North Africa is a region encompassing the northernmost countries of the African continent, characterized by its Sahara Desert landscapes, Mediterranean coastline, and a cultural blend of Arab, Berber, and African influences.
-
C.
Wilayat Gharb Ifriqiya
Wilayat Gharb Ifriqiya is the West Africa branch of the Islamic State militant organization, active primarily in the Lake Chad Basin and surrounding regions.
-
D.
AFRIQIYAH
AFRIQIYAH is the radio callsign used by Afriqiyah Airways, the state-owned flag carrier airline of Libya.
-
E.
المغرب العربي
المغرب العربي هو منطقة جغرافية وثقافية في شمال غرب إفريقيا تضم عدة دول عربية وتتميز بإرث حضاري إسلامي وأمازيغي عريق.
- 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_69e0c4618bec8190bcb0feb74568cbb1 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69eee9cef2748190990a81967d49b706 |
completed | April 27, 2026, 4:45 a.m. |
Created at: April 16, 2026, 6:30 p.m.