Triple
T25981571
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lilongwe City Council |
E646083
|
entity |
| Predicate | hasElectoralWards |
P148101
|
FINISHED |
| Object |
Lilongwe City wards
Lilongwe City wards are the local electoral divisions within Malawi’s capital city used to elect representatives to the Lilongwe City Council.
|
E1703158
|
NE FINISHED |
How this triple was built (3 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: Lilongwe City wards | Statement: [Lilongwe City Council, hasElectoralWards, Lilongwe City wards]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Lilongwe City wards Triple: [Lilongwe City Council, hasElectoralWards, Lilongwe City wards]
Generated description
Lilongwe City wards are the local electoral divisions within Malawi’s capital city used to elect representatives to the Lilongwe City Council.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasElectoralWards Context triple: [Lilongwe City Council, hasElectoralWards, Lilongwe City wards]
-
A.
hasMunicipalWards
chosen
Indicates that a municipality is divided into and associated with one or more municipal wards as its internal administrative units.
-
B.
hasElectoralDistricts
Indicates that a political or administrative unit is divided into one or more electoral districts used for representation or voting.
-
C.
hasElectoralWardStatus
Indicates that an entity holds the official status or designation of an electoral ward within an administrative or political system.
-
D.
hasElectoralUnit
Indicates that a political or administrative entity is associated with a specific electoral unit used for voting or representation.
-
E.
hasParallelElectorates
Indicates that two electoral systems or jurisdictions share corresponding or equivalent electorates that function in parallel.
- F. None of above.
Provenance (6 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_69e77e881fc08190ba1c8dc7e2a07f97 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f60c698ae48190871cd445422bad91 |
completed | May 2, 2026, 2:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a11078ff24481908ee159fa05d6397d |
completed | May 23, 2026, 1:49 a.m. |
| NEDg | Description generation | batch_6a11085043a08190b86f770075f609c1 |
completed | May 23, 2026, 1:52 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a110925bec881908c0bdb63355e4e31 |
completed | May 23, 2026, 1:55 a.m. |
| PD | Predicate disambiguation | batch_69f60b874cc88190a487230abb69efea |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 22, 2026, 8:54 a.m.