Triple
T35246102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WCHL Most Valuable Player |
E1017665
|
entity |
| Predicate | laterKnownAsLeague |
P48065
|
FINISHED |
| Object | Western Hockey League |
—
|
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: Western Hockey League | Statement: [WCHL Most Valuable Player, laterKnownAsLeague, Western Hockey League]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterKnownAsLeague Context triple: [WCHL Most Valuable Player, laterKnownAsLeague, Western Hockey League]
-
A.
laterLeagueName
chosen
Indicates that an entity’s league name was changed to a different (later) league name at some point in time.
-
B.
formerLeagueNameFor
Indicates that one league name was previously used for, but has since been replaced by, the current name of a league.
-
C.
previousLeagueNameUsage
Indicates that an entity previously used a different league name during an earlier period or context.
-
D.
namedAfterLeague
Indicates that one entity has been given a name derived from or in honor of a particular league.
-
E.
formerLeague
Indicates that an entity previously belonged to or participated in a particular league but is no longer a member.
- 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_69f76de235048190b990070c23c51b6b |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a005d878aec81908e1177914a8fb610 |
completed | May 10, 2026, 10:27 a.m. |
| PD | Predicate disambiguation | batch_6a005c382f8881908ff33ebb7f88c430 |
completed | May 10, 2026, 10:21 a.m. |
Created at: May 3, 2026, 4:02 p.m.