Triple
T24062424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madeline Island Ferry |
E595990
|
entity |
| Predicate | replacesDuringIceSeason |
P100564
|
FINISHED |
| Object | Madeline Island Ice Road |
—
|
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: Madeline Island Ice Road | Statement: [Madeline Island Ferry, replacesDuringIceSeason, Madeline Island Ice Road]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: replacesDuringIceSeason Context triple: [Madeline Island Ferry, replacesDuringIceSeason, Madeline Island Ice Road]
-
A.
tookPlaceInColdSeason
Indicates that the event or action occurred during a cold season of the year.
-
B.
hasSeasonalIceRoads
chosen
Indicates that temporary roads made of or over ice are available in certain seasons connecting the related entities.
-
C.
summerWinterCycle
Indicates a recurring transition between summer and winter seasons, capturing the cyclical change in conditions or states across these two periods.
-
D.
affectedSeason
Indicates that one entity has an influence on, or causes a change in, a particular season.
-
E.
recreationSeason
Indicates the time of year or specific season during which a recreational activity, facility, or area is typically used or available.
- 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_69e288c25c008190850cf447940ab181 |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1da5825548190b94cb6e708617a7d |
completed | April 29, 2026, 10:15 a.m. |
| PD | Predicate disambiguation | batch_69f1764b1d4c8190b12590c6339c31c1 |
completed | April 29, 2026, 3:08 a.m. |
Created at: April 17, 2026, 10:38 p.m.