Triple
T8634644
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zege Peninsula |
E204490
|
entity |
| Predicate | locatedOnSideOfLake |
P31095
|
FINISHED |
| Object | southern shore of Lake Tana |
—
|
LITERAL 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: southern shore of Lake Tana | Statement: [Zege Peninsula, locatedOnSideOfLake, southern shore of Lake Tana]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedOnSideOfLake Context triple: [Zege Peninsula, locatedOnSideOfLake, southern shore of Lake Tana]
-
A.
hasNearbyLake
Indicates that one entity is located close to or in the vicinity of a lake.
-
B.
isInLake
Indicates that one entity is located within the body of water defined as a lake.
-
C.
situatedOnSideOf
chosen
Indicates that one entity is located along or beside the lateral part or edge of another entity.
-
D.
locatedInFormerLake
Indicates that an entity is situated within the area that was once occupied by a lake that no longer exists.
-
E.
connectsToByLake
Indicates that one entity is linked or joined to another specifically via a lake as the connecting medium or route.
- F. None of above.
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_69ca834b903c8190add96cc651e1a477 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc47944d1c819081f448f14d04bf9d |
completed | March 31, 2026, 10:15 p.m. |
| PD | Predicate disambiguation | batch_69cc455d6d448190a2da2a319ac78c37 |
completed | March 31, 2026, 10:06 p.m. |
Created at: March 30, 2026, 6:27 p.m.