Triple
T9339892
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dallas Stars–New York Rangers games |
E224736
|
entity |
| Predicate | team1Origin |
P74477
|
FINISHED |
| Object | Dallas Stars relocated from Minnesota North Stars in 1993 |
—
|
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: Dallas Stars relocated from Minnesota North Stars in 1993 | Statement: [Dallas Stars–New York Rangers games, team1Origin, Dallas Stars relocated from Minnesota North Stars in 1993]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: team1Origin Context triple: [Dallas Stars–New York Rangers games, team1Origin, Dallas Stars relocated from Minnesota North Stars in 1993]
-
A.
teamOrigin
chosen
Indicates the place, organization, or context from which a team originates or is formed.
-
B.
originalTeam
Indicates that an entity was initially or first associated with a particular team, before any subsequent changes or transfers.
-
C.
team1
Indicates that the referenced entity is the first team or side participating in a competitive or relational context.
-
D.
originalTeam2Name
Indicates the name of the second team as it was originally designated or recorded.
-
E.
institutionalAffiliationTeam1
Indicates that an entity is formally affiliated with or belongs to the first team of an institution.
- 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_69ca84286fcc81909f6e7fd7a7e862a2 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd4bae2e2481909effc2dc89a642c5 |
completed | April 1, 2026, 4:45 p.m. |
| PD | Predicate disambiguation | batch_69cc7a66aef08190b8d668cff5b04f5f |
completed | April 1, 2026, 1:52 a.m. |
Created at: March 30, 2026, 7:40 p.m.