Triple
T25602026
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2007 NHL All-Star Game |
E641811
|
entity |
| Predicate | nextNHLAll-StarGame |
P107143
|
FINISHED |
| Object | 2008 NHL All-Star Game |
—
|
NE NERFINISHED |
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: 2008 NHL All-Star Game | Statement: [2007 NHL All-Star Game, nextNHLAll-StarGame, 2008 NHL All-Star Game]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nextNHLAll-StarGame Context triple: [2007 NHL All-Star Game, nextNHLAll-StarGame, 2008 NHL All-Star Game]
-
A.
cityHostFirstNHLAllStarGame
Indicates that a city is the location where the NHL All-Star Game was held for the very first time.
-
B.
isNHLAllStar
Indicates that the person has been selected to participate as an All-Star in the National Hockey League (NHL).
-
C.
nextAllStarGame
chosen
Indicates that one entity is the immediately upcoming All-Star Game event relative to another reference point (such as a league, season, or date).
-
D.
NHLAllStarAppearances
Indicates the number of times an entity has participated in an NHL All-Star Game.
-
E.
KHLAllStar
Indicates that an individual has been selected to participate in a Kontinental Hockey League (KHL) All-Star event or team.
- 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_69e75dc60d108190b7e2419e36b0134b |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f9a7d7d881909014fdf3746f981b |
completed | May 2, 2026, 1:18 p.m. |
| PD | Predicate disambiguation | batch_69f480789be08190ab252a6de3797200 |
completed | May 1, 2026, 10:29 a.m. |
Created at: April 21, 2026, 4:31 p.m.