Triple
T15998675
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | World Figure Skating Championships |
E388040
|
entity |
| Predicate | competitionFormatIceDance |
P121230
|
FINISHED |
| Object | rhythm dance |
—
|
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: rhythm dance | Statement: [World Figure Skating Championships, competitionFormatIceDance, rhythm dance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: competitionFormatIceDance Context triple: [World Figure Skating Championships, competitionFormatIceDance, rhythm dance]
-
A.
winnerIceDance
Indicates that one entity is the winner of an ice dance competition or event in relation to another specified context (such as a competition, year, or performance).
-
B.
championIceDance
Indicates that one entity is the champion in the discipline of ice dance, typically in relation to a specific competition, event, or title.
-
C.
skatingDiscipline
Indicates the specific type or category of skating discipline associated with an entity (e.g., figure, speed, ice dance).
-
D.
iceDanceChampion
Indicates that the subject is the winner or titleholder of a competitive ice dancing event or championship.
-
E.
skating style
Indicates the particular technique or manner in which an entity performs skating.
- 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_69d86daa562c81908aacc179c0fe8fb5 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e17d4e871c819082d7b1c1eaf5b4fe |
completed | April 17, 2026, 12:22 a.m. |
| PD | Predicate disambiguation | batch_69e142d9d8e881909b559a3e3ca21d24 |
completed | April 16, 2026, 8:13 p.m. |
| PDg | Predicate description generation | batch_69e17d48cc9c8190b03fd07ae2e9dfd8 |
completed | April 17, 2026, 12:22 a.m. |
Created at: April 10, 2026, 4:55 a.m.