Triple
T31607523
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rotonui (big lake) |
E806532
|
entity |
| Predicate | isPrincipalFreshwaterLakeOf |
P19444
|
FINISHED |
| Object | Mitiaro |
—
|
NE NERFINISHED |
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: Mitiaro | Statement: [Rotonui (big lake), isPrincipalFreshwaterLakeOf, Mitiaro]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isPrincipalFreshwaterLakeOf Context triple: [Rotonui (big lake), isPrincipalFreshwaterLakeOf, Mitiaro]
-
A.
isInlandLake
Indicates that a body of water is a lake located inland, not directly connected to the sea or ocean.
-
B.
isFreshwaterBody
Indicates that the referenced body of water consists primarily of non-saline (fresh) water rather than saltwater.
-
C.
hasFreshwaterLake
Indicates that one entity possesses, contains, or is associated with a freshwater lake.
-
D.
lakeIsOneOf
Indicates that the subject lake belongs to a specified set or category of lakes.
-
E.
isLargestFreshwaterLakeIn
chosen
Indicates that a lake is the largest freshwater lake within the specified geographic region or area.
- 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_69f348d61f2081908cad94bc9ffbb671 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69fcdf2394748190b35cead3e208447d |
completed | May 7, 2026, 6:51 p.m. |
| PD | Predicate disambiguation | batch_69fcdbe344ec8190a0471911952f4b82 |
completed | May 7, 2026, 6:37 p.m. |
Created at: April 30, 2026, 10:35 p.m.