Triple
T8634675
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zege Peninsula |
E204490
|
entity |
| Predicate | languageSpoken |
P151
|
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: [Zege Peninsula, languageSpoken, Amharic]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Amharic Context triple: [Zege Peninsula, languageSpoken, 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 refers to a person from Ethiopia or of Ethiopian descent, associated with the country's distinct cultures, languages, and history in the Horn of Africa.
-
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.
ETHIOPIAN
ETHIOPIAN is the radio callsign used by Ethiopian Airlines for its flight operations and air traffic communications.
- 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_69ca834b903c8190add96cc651e1a477 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc475fb9dc8190bd0d6e5edd05ea79 |
completed | March 31, 2026, 10:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cebc1b330c81909ff8a6806401dfd1 |
completed | April 2, 2026, 6:57 p.m. |
Created at: March 30, 2026, 6:27 p.m.