Triple
T2403408
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gumuz languages |
E50219
|
entity |
| Predicate | languageContactWith |
P22730
|
FINISHED |
| Object | Amharic |
E41109
|
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: Amharic | Statement: [Gumuz languages, languageContactWith, Amharic]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amharic Context triple: [Gumuz languages, languageContactWith, Amharic]
-
A.
Amharic
chosen
Amharic is a Semitic language widely spoken in Ethiopia and used as a major language of government, education, and media in the country.
-
B.
Tigrinya
Tigrinya is a Semitic language spoken primarily in Eritrea and northern Ethiopia, serving as a major language of communication, education, and media in the region.
-
C.
ETHIOPIAN
ETHIOPIAN is the radio callsign used by Ethiopian Airlines for its flight operations and air traffic communications.
-
D.
Oromo
Oromo is a Cushitic language widely spoken by the Oromo people, primarily in Ethiopia and parts of neighboring East African countries.
-
E.
Ge'ez
Ge'ez is an ancient Semitic language of Ethiopia and Eritrea, best known today as the classical and liturgical language of the Ethiopian and Eritrean Orthodox Tewahedo Churches.
- 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_69a88b0339a88190a1207333cd271cc9 |
completed | March 4, 2026, 7:41 p.m. |
| NER | Named-entity recognition | batch_69abc8f8aa2881909192920ee394f0b3 |
completed | March 7, 2026, 6:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69aeb3e740c88190872aa1a7834d73b0 |
completed | March 9, 2026, 11:49 a.m. |
Created at: March 4, 2026, 7:58 p.m.