Triple
T11479768
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Montreal Canadiens–Boston Bruins rivalry |
E272112
|
entity |
| Predicate | team2FranchiseStart |
P99515
|
FINISHED |
| Object | 1924 |
—
|
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: 1924 | Statement: [Montreal Canadiens–Boston Bruins rivalry, team2FranchiseStart, 1924]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: team2FranchiseStart Context triple: [Montreal Canadiens–Boston Bruins rivalry, team2FranchiseStart, 1924]
-
A.
team2Franchise
Indicates a relationship where a second team is associated with, or belongs to, a particular franchise.
-
B.
team1Franchise
Indicates that an entity serves as or represents the franchise associated with the first team in a given sports or competitive context.
-
C.
teamStartYear
Indicates the year in which an entity (such as a person or organization) began its association with a particular team.
-
D.
hostTeamFranchise
Indicates that a team franchise is serving as the host team in a given game or event.
-
E.
playsForFranchise
Indicates that one entity is an athlete or performer who is a member of, or competes on behalf of, a particular sports franchise or team.
- 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_69d6aae0c8d881908a5a360c0be3242e |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8294f0e948190b2e106beb86e4b2c |
completed | April 9, 2026, 10:33 p.m. |
| PD | Predicate disambiguation | batch_69d8086ecd6c81908f424864857762d6 |
completed | April 9, 2026, 8:13 p.m. |
| PDg | Predicate description generation | batch_69d8279925e4819089210611c0d8e61a |
completed | April 9, 2026, 10:26 p.m. |
Created at: April 8, 2026, 9:36 p.m.