Triple
T33431592
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Japan vs South Africa (2015 Rugby World Cup) |
E856144
|
entity |
| Predicate | favouriteTeam |
P13627
|
FINISHED |
| Object | South Africa national rugby union team |
—
|
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: South Africa national rugby union team | Statement: [Japan vs South Africa (2015 Rugby World Cup), favouriteTeam, South Africa national rugby union team]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: favouriteTeam Context triple: [Japan vs South Africa (2015 Rugby World Cup), favouriteTeam, South Africa national rugby union team]
-
A.
favoriteTeam
chosen
Indicates that one entity is the sports team preferred above all others by another entity.
-
B.
sportOfReferencedTeam
Indicates that the subject is the sport played by, or associated with, the referenced team.
-
C.
homeStadiumSupportedTeam
Indicates that a particular stadium serves as the primary home venue for a specific sports team.
-
D.
ownsProfessionalTeam
Indicates that one entity has legal ownership or controlling interest in a professional sports team.
-
E.
leagueTeam
Indicates that a team is a member or participant of a particular league.
- 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_69f349709e7881908c342b4d34f555f4 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6e48010788190bd60e56b378f4b4a |
completed | May 3, 2026, 6 a.m. |
| PD | Predicate disambiguation | batch_69f6e3da41948190a4cfe866ce184f73 |
completed | May 3, 2026, 5:57 a.m. |
Created at: May 1, 2026, 1:36 a.m.