Triple
T9355993
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States at the 2002 Winter Olympics |
E225140
|
entity |
| Predicate | sportContested |
P88122
|
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: [United States at the 2002 Winter Olympics, sportContested, alpine skiing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sportContested Context triple: [United States at the 2002 Winter Olympics, sportContested, alpine skiing]
-
A.
alsoContestedSports
Indicates that two or more entities have also competed against each other in sports contests, in addition to any primary relationship already specified.
-
B.
sportFocus
Indicates that one entity has a primary emphasis, specialization, or concentration on a particular sport represented by the other entity.
-
C.
sportsCount
Indicates the number of sports associated with or involved in a given entity or context.
-
D.
sportsCategory
Indicates that one entity is classified as a type or category within the domain of sports to which the other entity belongs.
-
E.
sportsVariant
Indicates that one sport is a variation, subtype, or modified form of another sport.
- F. None of above. chosen
Provenance (4 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_69ca842abfd48190949d71c3b86eeba8 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd4fee9d4c8190a7d121c9487ccca2 |
completed | April 1, 2026, 5:03 p.m. |
| PD | Predicate disambiguation | batch_69cc7a68ab9481909f97cb70764697cc |
completed | April 1, 2026, 1:52 a.m. |
| PDg | Predicate description generation | batch_69cc955a38108190b602d1e73725f11b |
completed | April 1, 2026, 3:47 a.m. |
Created at: March 30, 2026, 7:42 p.m.