Triple
T9066914
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beni-Amir |
E217266
|
entity |
| Predicate | usesLanguage |
P238
|
FINISHED |
| Object | Tigrinya language |
E41857
|
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: Tigrinya language | Statement: [Beni-Amir, usesLanguage, Tigrinya language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tigrinya language Context triple: [Beni-Amir, usesLanguage, Tigrinya language]
-
A.
Tigrinya
chosen
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.
-
B.
Amharic
Amharic is a Semitic language widely spoken in Ethiopia and used as a major language of government, education, and media in the country.
-
C.
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.
-
D.
Eritrean
Eritrean refers to someone or something originating from Eritrea, a country in the Horn of Africa known for its diverse ethnic groups and Red Sea coastline.
-
E.
ትግርኛ
ትግርኛ is a Semitic language primarily spoken in Eritrea and northern Ethiopia by the Tigrinya people.
- 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_69ca83d5a7f48190b16c1e59bd43ede0 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc94bde9c08190a4f568fbccc3c3e9 |
completed | April 1, 2026, 3:45 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d017a3926881909140f59c60ec3588 |
completed | April 3, 2026, 7:40 p.m. |
Created at: March 30, 2026, 7:11 p.m.