Triple
T22329721
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ra II papyrus boat |
E551990
|
entity |
| Predicate | departurePort |
P1521
|
FINISHED |
| Object | Safi, Morocco |
—
|
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: Safi, Morocco | Statement: [Ra II papyrus boat, departurePort, Safi, Morocco]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Safi, Morocco Context triple: [Ra II papyrus boat, departurePort, Safi, Morocco]
-
A.
Skhirat, Morocco
Skhirat, Morocco is a coastal town near Rabat known for hosting key international diplomatic negotiations and political agreements.
-
B.
Guelmim
Guelmim is a city in southern Morocco known as a gateway to the Sahara and a regional center for Saharan trade and culture.
-
C.
Al Hoceima
Al Hoceima is a coastal city in northern Morocco on the Mediterranean, known as a major urban center of the Rif region and an important hub for the Riffian (Amazigh) population.
-
D.
Marrakesh-Safi
chosen
Marrakesh-Safi is an administrative region in central-western Morocco known for the historic city of Marrakesh and its Atlantic coastline around Safi.
-
E.
Maghreb de Fès
Maghreb de Fès is a prominent Moroccan football club based in the city of Fez, known for its passionate fan base and domestic successes.
- 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_69e11e482f788190b78d1588fc26d606 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1576ab52c819087563cd778d6bc5e |
completed | April 29, 2026, 12:57 a.m. |
Created at: April 16, 2026, 8:43 p.m.