Triple
T18747273
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Red Sea trade corridor |
E458435
|
entity |
| Predicate | includesPort |
P65472
|
FINISHED |
| Object | Suakin |
—
|
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: Suakin | Statement: [Red Sea trade corridor, includesPort, Suakin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Suakin Context triple: [Red Sea trade corridor, includesPort, Suakin]
-
A.
Suakin
chosen
Suakin is a historic port city on Sudan’s Red Sea coast that was once a major hub for trade and pilgrimage between Africa and the Arabian Peninsula.
-
B.
Sakaar
Sakaar is a chaotic, trash-covered planet ruled by the Grandmaster in the Marvel Cinematic Universe, known for its gladiatorial contests and bizarre cosmic detritus.
-
C.
Sukeva
Sukeva is a village in northern Finland best known for housing the Sukevan vankila prison facility.
-
D.
Senyavin
Senyavin is a Russian surname most notably associated with a family of naval officers and admirals in the Imperial Russian Navy.
-
E.
Surlej
Surlej is a small hamlet in the municipality of Silvaplana in Switzerland’s Upper Engadine region, known for its scenic alpine setting near Lake Silvaplana.
- 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_69d8d394dc308190b6725073f5db324c |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e576936cf08190b3c0d2f4e8a616fc |
completed | April 20, 2026, 12:42 a.m. |
Created at: April 10, 2026, 11:51 a.m.