Triple
T10184923
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mengistu Haile Mariam |
E236882
|
entity |
| Predicate | residence |
P75
|
FINISHED |
| Object | Harare, Zimbabwe |
E8616
|
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: Harare, Zimbabwe | Statement: [Mengistu Haile Mariam, residence, Harare, Zimbabwe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harare, Zimbabwe Context triple: [Mengistu Haile Mariam, residence, Harare, Zimbabwe]
-
A.
Harare
chosen
Harare is the largest city and main economic, political, and cultural center of Zimbabwe.
-
B.
Masvingo
Masvingo is one of Zimbabwe’s oldest urban centers, located in the country’s southeastern region near the Great Zimbabwe ruins.
-
C.
Bulawayo
Bulawayo is Zimbabwe’s second-largest city and a major industrial, cultural, and transport hub in the southwestern part of the country.
-
D.
Chivhu, Zimbabwe
Chivhu, Zimbabwe is a small town in central Zimbabwe known as an agricultural center and one of the country’s oldest European-settled communities.
-
E.
Marondera
Marondera is a town in eastern Zimbabwe known as an agricultural and educational center within the Mashonaland region.
- 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_69ca84d7260c8190bfbec36762943f37 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cded36e9808190b385c5aec4889e00 |
completed | April 2, 2026, 4:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d317a4d99c8190941322d3de2998f5 |
completed | April 6, 2026, 2:17 a.m. |
Created at: March 30, 2026, 9:12 p.m.