Triple
T28768787
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Renate Götschl |
E726349
|
entity |
| Predicate | WorldChampionshipTitleEvent |
P89163
|
FINISHED |
| Object | downhill |
—
|
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: downhill | Statement: [Renate Götschl, WorldChampionshipTitleEvent, downhill]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: WorldChampionshipTitleEvent Context triple: [Renate Götschl, WorldChampionshipTitleEvent, downhill]
-
A.
WorldChampionshipsEvent
chosen
Indicates an event that is part of, or constitutes, a world-level championship competition.
-
B.
worldChampionshipTitles
Indicates the number of world championship titles an entity has won.
-
C.
worldChampionshipsOrganiser
Indicates that the subject is responsible for organizing or managing world championship events for the object.
-
D.
worldChampionshipTitleYear
Indicates the specific year in which an entity won a world championship title.
-
E.
worldTitles
Indicates that an entity has won one or more world championship titles in a given field or competition.
- 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_69f03198be14819098fa74e48b3749bf |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f7bbf906d8819099020e548dd56bc9 |
completed | May 3, 2026, 9:19 p.m. |
| PD | Predicate disambiguation | batch_69f7b9a2dcf88190a7c9e109e41267be |
completed | May 3, 2026, 9:09 p.m. |
Created at: April 28, 2026, 6:14 a.m.