Triple
T12255794
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Minnesota state high school girls ice hockey championships |
E292095
|
entity |
| Predicate | typeOfHockey |
P103747
|
FINISHED |
| Object | ice hockey |
—
|
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: ice hockey | Statement: [Minnesota state high school girls ice hockey championships, typeOfHockey, ice hockey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfHockey Context triple: [Minnesota state high school girls ice hockey championships, typeOfHockey, ice hockey]
-
A.
playsOnRinkType
Indicates that an entity participates in a game or activity on a specific type of rink surface or rink configuration.
-
B.
NHLTeamType
Indicates the classification or category of an NHL team, such as its type or role within the league structure.
-
C.
playsIceHockeyCode
Indicates that one entity participates in ice hockey under the specific code, ruleset, or organizational classification represented by the other entity.
-
D.
iceRinkType
Indicates the specific kind or category of an ice rink associated with an entity (e.g., indoor, outdoor, Olympic-sized).
-
E.
iceSurface
Indicates that something is located on, in contact with, or forming the surface of ice.
- 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_69d6ab67950c8190be08450a06228c4b |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d91d38ee10819093ed41d2954bf4ef |
completed | April 10, 2026, 3:54 p.m. |
| PD | Predicate disambiguation | batch_69d91c46dcd88190a263db30804bff36 |
completed | April 10, 2026, 3:50 p.m. |
| PDg | Predicate description generation | batch_69d91d3654208190a2e0487dfa1d54da |
completed | April 10, 2026, 3:54 p.m. |
Created at: April 8, 2026, 9:52 p.m.