Triple
T19531636
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ski Train to Winter Park |
E488669
|
entity |
| Predicate | servedActivity |
P19746
|
FINISHED |
| Object | alpine skiing |
—
|
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: alpine skiing | Statement: [Ski Train to Winter Park, servedActivity, alpine skiing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servedActivity Context triple: [Ski Train to Winter Park, servedActivity, alpine skiing]
-
A.
servedUntil
Indicates the ending time or date up to which an entity held a position, role, or service.
-
B.
served
Indicates that one entity provided a service, assistance, or role-based function to or for another entity.
-
C.
hasActivityIn
chosen
Indicates that an entity engages in or performs a particular activity within a specified context, location, or domain.
-
D.
awardedForActivitiesIn
Indicates that an award or recognition is given to an entity specifically because of activities carried out in a particular field, context, or domain.
-
E.
servedDuring
Indicates that one entity held a role, position, or performed a function within the time period defined by 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_69d8e8db5b6c8190984b61f91981f575 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6363fd1f8819080805346efad2579 |
completed | April 20, 2026, 2:20 p.m. |
| PD | Predicate disambiguation | batch_69e514c9c00481909b76bda67957e58b |
completed | April 19, 2026, 5:45 p.m. |
Created at: April 10, 2026, 1:41 p.m.