Triple
T17074656
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United Hockey League |
E414316
|
entity |
| Predicate | typicalRegularSeasonGames |
P7554
|
FINISHED |
| Object | 76 |
—
|
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: 76 | Statement: [United Hockey League, typicalRegularSeasonGames, 76]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalRegularSeasonGames Context triple: [United Hockey League, typicalRegularSeasonGames, 76]
-
A.
regularSeasonGamesPerTeam
chosen
Indicates the number of games each team plays during the regular season.
-
B.
regularSeasonGamesPlayed
Indicates the number of games an entity participated in during the regular season of a competition or league.
-
C.
playedRegularSeasonGamesIn
Indicates that an athlete participated in one or more regular-season games for a specified team or league.
-
D.
regularSeasonWins
Indicates the number of games a team wins during the regular season of a competition.
-
E.
seriesRegularSeasons
Indicates the seasons of a series during which an entity (such as an actor or character) is a regular, ongoing part of the main cast.
- 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_69d886cef44c8190ba56c44b4e863e64 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dbc3b69c819093b32da3998eed46 |
completed | April 18, 2026, 7:30 p.m. |
| PD | Predicate disambiguation | batch_69e35d642f74819098c014135e249b27 |
completed | April 18, 2026, 10:31 a.m. |
Created at: April 10, 2026, 5:34 a.m.