Triple
T22780362
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeongseon Alpine Centre |
E563819
|
entity |
| Predicate | olympicEventHosted |
P69518
|
FINISHED |
| Object | men's 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: men's downhill | Statement: [Jeongseon Alpine Centre, olympicEventHosted, men's downhill]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: olympicEventHosted Context triple: [Jeongseon Alpine Centre, olympicEventHosted, men's downhill]
-
A.
olympicSportHosted
chosen
Indicates that a particular Olympic sport was held or staged at a specific Olympic Games or host location.
-
B.
olympicGamesHosted
Indicates that a particular location or entity served as the host for a specific edition of the Olympic Games.
-
C.
olympicHostCountry
Indicates that a country served as the official host nation for a particular edition of the Olympic Games.
-
D.
olympicHostState
Indicates that a state served as the official host location for a particular edition of the Olympic Games.
-
E.
OlympicHostCity
Indicates that a city has been officially selected to host and organize a particular edition of the Olympic Games.
- 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_69e2455500788190b4b33030461f3bbd |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17c2cab0881908df1d0629b43d350 |
completed | April 29, 2026, 3:34 a.m. |
| PD | Predicate disambiguation | batch_69eed2c32e8c8190b73bb9965ed47d64 |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:28 p.m.