Triple
T14253155
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FRELIMO |
E353318
|
entity |
| Predicate | prominentLeader |
P1520
|
FINISHED |
| Object | Filipe Nyusi |
E1094120
|
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: Filipe Nyusi | Statement: [FRELIMO, prominentLeader, Filipe Nyusi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Filipe Nyusi Context triple: [FRELIMO, prominentLeader, Filipe Nyusi]
-
A.
Filipe Nyusi
chosen
Filipe Nyusi is a Mozambican politician who has served as the President of Mozambique since 2015 and is a prominent member of the FRELIMO party.
-
B.
Armando Guebuza
Armando Guebuza is a Mozambican politician and businessman who served as President of Mozambique from 2005 to 2015.
-
C.
João Lourenço
João Lourenço is an Angolan politician and former defense minister who has served as the country's president since 2017.
-
D.
Momolu Duwalu Bukele
Momolu Duwalu Bukele was a 19th-century Liberian innovator best known for inventing the indigenous Vai syllabary used to write the Vai language.
-
E.
Emmerson Mnangagwa
Emmerson Mnangagwa is a Zimbabwean politician and former guerrilla leader who became president in 2017 following the ouster of long-time leader Robert Mugabe.
- 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_69d8278c43e08190824146f4632b89a5 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de6297f38c819090d7c7fd8bfa2e9e |
completed | April 14, 2026, 3:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd5bb7e0ac81909d62993689b56f83 |
completed | May 8, 2026, 3:42 a.m. |
Created at: April 10, 2026, 1:09 a.m.