Triple
T16726621
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ngwathe Local Municipality Council |
E406479
|
entity |
| Predicate | hasJurisdictionOver |
P808
|
FINISHED |
| Object | Edenville |
E1230645
|
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: Edenville | Statement: [Ngwathe Local Municipality Council, hasJurisdictionOver, Edenville]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Edenville Context triple: [Ngwathe Local Municipality Council, hasJurisdictionOver, Edenville]
-
A.
Edenville
chosen
Edenville is a small town in the Free State province of South Africa.
-
B.
Luthersville
Luthersville is a small rural city in Meriwether County, Georgia, known for its quiet residential character and location in west-central Georgia.
-
C.
Unienville
Unienville is a small commune in the Aube department of north-central France.
-
D.
Mebanesville
Mebanesville was the original name of the city now known as Mebane in North Carolina.
-
E.
Yatesville
Yatesville is a small town located in the U.S. state of Georgia.
- 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_69d8838f242881908abd8bc138795886 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e38747e43c8190a44487c4a9c94c7b |
completed | April 18, 2026, 1:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00a518019881909a7c5ef344966579 |
completed | May 10, 2026, 3:32 p.m. |
Created at: April 10, 2026, 5:20 a.m.