Triple
T530280
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sea of Galilee |
E12206
|
entity |
| Predicate | isLowest |
P211
|
FINISHED |
| Object | lowest freshwater lake on Earth |
—
|
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: lowest freshwater lake on Earth | Statement: [Sea of Galilee, isLowest, lowest freshwater lake on Earth]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isLowest Context triple: [Sea of Galilee, isLowest, lowest freshwater lake on Earth]
-
A.
hasLow
Indicates that an entity possesses a value, level, or amount of something that is below a defined or expected threshold.
-
B.
isMinimumWhen
Indicates that a value or state is at its smallest or least level precisely under certain specified conditions or circumstances.
-
C.
lowestRank
Indicates that the subject has the least or worst rank in an ordered set compared to all other related entities.
-
D.
lowestPoint
chosen
Indicates that one entity is the point with the minimum vertical position or value relative to another entity or within a specified context.
-
E.
hasLower
Indicates that one entity is positioned at a lower level, rank, or value relative to another entity.
- 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_69a4933208e88190891f5debab1b776d |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4985e51908190a34aa82ea9dbee1e |
completed | March 1, 2026, 7:49 p.m. |
| PD | Predicate disambiguation | batch_69a494b257108190a537dffbb9d621b5 |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:32 p.m.