Triple
T34803430
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | OHL regular season |
E1003280
|
entity |
| Predicate | standingsUsedFor |
P10473
|
FINISHED |
| Object | OHL playoff seeding |
—
|
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: OHL playoff seeding | Statement: [OHL regular season, standingsUsedFor, OHL playoff seeding]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: standingsUsedFor Context triple: [OHL regular season, standingsUsedFor, OHL playoff seeding]
-
A.
standingsType
Indicates the category or format of a ranking or leaderboard in which entities are ordered or evaluated.
-
B.
standingsCriteria
Indicates the rules or factors used to determine the relative ranking or position of entities in a standings or leaderboard.
-
C.
hasStandings
Indicates that an entity possesses or is associated with a set of rankings, positions, or status levels within a competitive or comparative context.
-
D.
usesInStandingsTables
Indicates that something is employed or applied within standings tables, such as rankings or league tables, to represent or organize comparative positions.
-
E.
usesRegularSeasonStandingsFor
chosen
Indicates that one entity determines outcomes or decisions based on the regular season standings of another entity.
- 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_69f76db543808190b188c6c86a91491b |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69fcf1b3d9a08190850b388308656266 |
completed | May 7, 2026, 8:10 p.m. |
| PD | Predicate disambiguation | batch_69fcf0226d8c8190b23dceafb1794995 |
completed | May 7, 2026, 8:03 p.m. |
Created at: May 3, 2026, 3:59 p.m.