Triple
T11040982
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adigrat |
E261013
|
entity |
| Predicate | nearbyCity |
P350
|
FINISHED |
| Object | Mekelle |
E256050
|
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: Mekelle | Statement: [Adigrat, nearbyCity, Mekelle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mekelle Context triple: [Adigrat, nearbyCity, Mekelle]
-
A.
Mekelle
chosen
Mekelle is the largest city and administrative, economic, and cultural center of Ethiopia’s northern Tigray Region.
-
B.
Senafe
Senafe is a town in southern Eritrea known for its strategic location near the Ethiopian border and its surrounding highland landscapes.
-
C.
Massawa
Massawa is a historic Eritrean port city on the Red Sea, known for its strategic maritime location and Ottoman- and Italian-influenced architecture.
-
D.
Tantu
Tantu is a Kannada novel by acclaimed Indian writer S. L. Bhyrappa, known for its exploration of complex social and philosophical themes.
-
E.
Gafat
Gafat is an extinct South Ethio-Semitic language once spoken in parts of Ethiopia.
- 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_69d6aa979bdc8190bf0e79104cc098c1 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7980050948190ae7b187da5b776ca |
completed | April 9, 2026, 12:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e3a9e525508190bf3a728683eeec79 |
completed | April 18, 2026, 3:57 p.m. |
Created at: April 8, 2026, 9:26 p.m.