Triple
T14485401
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Greg Inglis |
E359215
|
entity |
| Predicate | NRLPremiershipYear |
P47838
|
FINISHED |
| Object | 2007 (with Melbourne Storm, later stripped) |
—
|
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: 2007 (with Melbourne Storm, later stripped) | Statement: [Greg Inglis, NRLPremiershipYear, 2007 (with Melbourne Storm, later stripped)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: NRLPremiershipYear Context triple: [Greg Inglis, NRLPremiershipYear, 2007 (with Melbourne Storm, later stripped)]
-
A.
premiershipsNRL
Indicates the number of National Rugby League (NRL) premiership titles an entity has won.
-
B.
wonNRLPremiership
chosen
Indicates that an entity has achieved victory in the National Rugby League (NRL) premiership competition.
-
C.
AFLPremiershipYear
Indicates the year in which a given team won the Australian Football League (AFL) premiership.
-
D.
yearWonWallyLewisMedal
Indicates the specific year in which an entity received the Wally Lewis Medal.
-
E.
AFLSeasons
Indicates the association between the Australian Football League and its individual seasons, linking the league to each specific season instance.
- 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_69d8279740308190af9df93a3af8592e |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de924d7f4c8190b1f62b5ffe1ff649 |
completed | April 14, 2026, 7:15 p.m. |
| PD | Predicate disambiguation | batch_69de5c487b4c819097803e58dca628a5 |
completed | April 14, 2026, 3:24 p.m. |
Created at: April 10, 2026, 1:20 a.m.