Triple
T401798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Drake Passage |
E9300
|
entity |
| Predicate | hasAverageSeaSurfaceTemperature |
P9307
|
FINISHED |
| Object | near freezing in winter |
—
|
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: near freezing in winter | Statement: [Drake Passage, hasAverageSeaSurfaceTemperature, near freezing in winter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAverageSeaSurfaceTemperature Context triple: [Drake Passage, hasAverageSeaSurfaceTemperature, near freezing in winter]
-
A.
hasAverageSurfaceTemperature
Indicates that an entity is associated with a specific mean value of its surface temperature over a defined period or condition.
-
B.
hasAverageSpringTemperature
Indicates that an entity is associated with a specific average temperature value measured over the spring season.
-
C.
averageTemperature
Indicates the typical or mean temperature value associated with an entity over a specified period or context.
-
D.
hasTemperature
Indicates that an entity possesses or is characterized by a specific temperature value.
-
E.
waterTemperatureType
chosen
Indicates the classification or category of a water body’s temperature (e.g., cold, warm, hot) associated with an entity or context.
- 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_69a2e8004cb88190b92ed1add6abf41a |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2ec9f77888190bcc2bc68d201ed35 |
completed | Feb. 28, 2026, 1:24 p.m. |
| PD | Predicate disambiguation | batch_69a2e96ee4ec8190a5c0e3f491d3963d |
completed | Feb. 28, 2026, 1:11 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.