Triple
T14034127
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ottoman conquest of Caffa |
E337665
|
entity |
| Predicate | location |
P40
|
FINISHED |
| Object | Caffa |
E67474
|
NE FINISHED |
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: Caffa | Statement: [Ottoman conquest of Caffa, location, Caffa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Caffa Context triple: [Ottoman conquest of Caffa, location, Caffa]
-
A.
Caffa
chosen
Caffa is the historical name of the Crimean port city now known as Feodosia, which was a major Genoese trading colony and a key Black Sea commercial hub in the Middle Ages.
-
B.
Kafa
Kafa is an Omotic language spoken primarily in southwestern Ethiopia by the Kafa people.
-
C.
Sidamo
Sidamo is a Cushitic language spoken primarily in southern Ethiopia by the Sidama people.
-
D.
Arabica
Arabica is a high-quality coffee species prized for its smooth, aromatic flavor and widely used in premium coffee varieties worldwide.
-
E.
Taza
Taza was a 19th-century Apache leader and the son of the famous chief Cochise, known for succeeding his father as a chief of the Chiricahua Apache.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d81c664e48819088cbd8f433aeffe5 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2fac71188190a586049405f1071e |
completed | April 14, 2026, 12:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fbc339d53c8190a9cd7027a716ff5f |
completed | May 6, 2026, 10:39 p.m. |
Created at: April 9, 2026, 10:20 p.m.