Triple
T14861959
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AFL clubs |
E349516
|
entity |
| Predicate | haveReservesTeamIn |
P71523
|
FINISHED |
| Object | state leagues |
—
|
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: state leagues | Statement: [AFL clubs, haveReservesTeamIn, state leagues]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: haveReservesTeamIn Context triple: [AFL clubs, haveReservesTeamIn, state leagues]
-
A.
hasReserveTeam
Indicates that an organization, typically a sports club, maintains a secondary or backup team formally associated with its main team.
-
B.
hasTeamFor
Indicates that an entity possesses, is associated with, or is responsible for a specific team designated for a particular purpose or context.
-
C.
hasReserveTeamLeagues
chosen
Indicates that an entity’s reserve team participates in, or is associated with, one or more specific sports leagues.
-
D.
hasCurrentTeam
Indicates that an entity is presently a member of or affiliated with a specific team.
-
E.
hasTeamSide
Indicates that an entity is associated with or belongs to a particular side or faction of a team within a competitive or collaborative context.
- 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_69d822ed7e1881909b90fca143ad7e34 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69ded573cba881908d6d9ac570a64e5f |
completed | April 15, 2026, 12:01 a.m. |
| PD | Predicate disambiguation | batch_69de8c1798c08190b433e9ad21e41a42 |
completed | April 14, 2026, 6:48 p.m. |
Created at: April 10, 2026, 1:54 a.m.