Triple
T28106030
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | London fog |
E710363
|
entity |
| Predicate | occursInWeatherCondition |
P134282
|
FINISHED |
| Object | cold, still air |
—
|
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: cold, still air | Statement: [London fog, occursInWeatherCondition, cold, still air]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: occursInWeatherCondition Context triple: [London fog, occursInWeatherCondition, cold, still air]
-
A.
hasWeather
Indicates that a location or environment is experiencing or characterized by a particular type of weather condition.
-
B.
weatherCondition
Indicates the type of atmospheric state or weather pattern (e.g., sunny, rainy, snowy) affecting a location or time period.
-
C.
isWeatherProtected
Indicates that an entity is shielded from or resistant to adverse weather conditions.
-
D.
hasWeatherContext
chosen
Indicates that something is associated with, influenced by, or described in terms of specific weather conditions or patterns.
-
E.
hasMinimumWeatherRequirements
Indicates that a subject is associated with the lowest acceptable set of weather conditions required for a particular activity, operation, or state to occur.
- 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_69ef9b71fdb081908b4a61cd7ff147c1 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f65f7731e4819099d5bd3d915ee266 |
completed | May 2, 2026, 8:32 p.m. |
| PD | Predicate disambiguation | batch_69f65c2198208190a3954086c22cfcbf |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 27, 2026, 9:08 p.m.