Triple
T37381894
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2022 IIHF World Championship |
E928452
|
entity |
| Predicate | originalHostCities |
P77932
|
FINISHED |
| Object | Helsinki |
E14163
|
NE 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: Helsinki | Statement: [2022 IIHF World Championship, originalHostCities, Helsinki]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalHostCities Context triple: [2022 IIHF World Championship, originalHostCities, Helsinki]
-
A.
originalHostCity
chosen
Indicates the city where an event or organization was first hosted or based before any subsequent relocations.
-
B.
formerHostCity
Indicates that a city previously served as the host location for a particular event or series of events, but no longer holds that role.
-
C.
numberOfHostCities
Indicates the count of distinct cities that have hosted or will host a particular event or activity.
-
D.
originalFinalHostCity
Indicates that a city was initially selected as the host city for an event but was later replaced by a different final host city.
-
E.
previousHostCity
Indicates that one city served as the immediately preceding host city relative to another in a sequence of hosting events.
- F. None of above.
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_69f76eb9e66881908534cf22d04c3b5a |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a40951c3d9c81909ab68a963f2284ad |
completed | June 28, 2026, 3:29 a.m. |
| PD | Predicate disambiguation | batch_6a037a13a1308190a202df66f4781855 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:16 p.m.