Triple
T1524096
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake Tanganyika |
E32295
|
entity |
| Predicate | rankByVolume |
P12242
|
FINISHED |
| Object | second-largest freshwater lake by volume in the world |
—
|
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: second-largest freshwater lake by volume in the world | Statement: [Lake Tanganyika, rankByVolume, second-largest freshwater lake by volume in the world]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rankByVolume Context triple: [Lake Tanganyika, rankByVolume, second-largest freshwater lake by volume in the world]
-
A.
rankedBy
Indicates that one entity is ordered or assigned a position in a hierarchy or list according to criteria determined or applied by another entity.
-
B.
rankBySize
Indicates that entities are ordered or compared based on their size.
-
C.
rankingType
chosen
Indicates the specific basis or method by which items are ordered or ranked relative to one another.
-
D.
depthRank
Indicates the relative ordering of entities based on how deep or distant they are along a specified depth dimension or hierarchy.
-
E.
rankByReserveHoldings
Indicates an ordering of entities based on the size or value of their reserve holdings, typically from highest to lowest.
- 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_69a885e9b0ac819093a9806ad0efc82c |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a93d4756888190bf3872154de11539 |
completed | March 5, 2026, 8:22 a.m. |
| PD | Predicate disambiguation | batch_69a907ac7ea081908dd95bb5cc3b9847 |
completed | March 5, 2026, 4:33 a.m. |
Created at: March 4, 2026, 7:26 p.m.