Triple
T20891500
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Béni Mellal-Khénifra |
E514417
|
entity |
| Predicate | containsCity |
P294
|
FINISHED |
| Object | Khénifra |
—
|
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: Khénifra | Statement: [Béni Mellal-Khénifra, containsCity, Khénifra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Khénifra Context triple: [Béni Mellal-Khénifra, containsCity, Khénifra]
-
A.
Khénifra
chosen
Khénifra is a city in central Morocco known as a cultural center of the Zayan Berber tribes and a gateway to the Middle Atlas mountains.
-
B.
Tashmetu
Tashmetu is a Mesopotamian goddess associated with mercy and the granting of prayers, venerated alongside the god Nabu.
-
C.
Neferu
Neferu is an ancient Egyptian female name borne by several royal women, including queens and princesses of the Middle and New Kingdoms.
-
D.
Hophra
Hophra was a pharaoh of Egypt’s 26th Dynasty, known for his military campaigns and eventual overthrow amid internal unrest and foreign pressure.
-
E.
Tawosret
Tawosret was a queen and the last pharaoh of Egypt’s 19th Dynasty, who briefly ruled as a female king during a period of political instability.
- 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_69e0b4f7ebe48190952a85547a0f31a1 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6d05e307081908f1d044e877017ec |
completed | April 21, 2026, 1:18 a.m. |
Created at: April 16, 2026, 12:46 p.m.