Triple
T15431086
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Greater Western Sydney |
E369639
|
entity |
| Predicate | sportsTeamOfType |
P48352
|
FINISHED |
| Object | Australian rules football club |
—
|
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: Australian rules football club | Statement: [Greater Western Sydney, sportsTeamOfType, Australian rules football club]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sportsTeamOfType Context triple: [Greater Western Sydney, sportsTeamOfType, Australian rules football club]
-
A.
sportsTeamPartialReturn
Indicates that a sports team has returned to competition or activity in a limited, incomplete, or transitional manner rather than fully resuming.
-
B.
sportsTeamOwned
Indicates that one entity is the owner (or part-owner) of a sports team entity.
-
C.
sportOfReferencedTeam
chosen
Indicates that the subject is the sport played by, or associated with, the referenced team.
-
D.
teamNameType
Indicates the type or category associated with a team's name (e.g., formal name, short name, nickname).
-
E.
sportsTeamPlaysIn
Indicates that a sports team regularly plays its home games or is based in a particular venue, city, or location.
- 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_69d85a1849f48190bf898068b2806fae |
completed | April 10, 2026, 2:02 a.m. |
| NER | Named-entity recognition | batch_69e03ed8ea888190bff8dc14859cca31 |
completed | April 16, 2026, 1:43 a.m. |
| PD | Predicate disambiguation | batch_69ded27f45548190a6d2b1b85cb47444 |
completed | April 14, 2026, 11:49 p.m. |
Created at: April 10, 2026, 3:21 a.m.