Triple
T20715161
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kallum Watkins |
E509149
|
entity |
| Predicate | typeOfSportPerson |
P33092
|
FINISHED |
| Object | rugby league player |
—
|
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: rugby league player | Statement: [Kallum Watkins, typeOfSportPerson, rugby league player]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfSportPerson Context triple: [Kallum Watkins, typeOfSportPerson, rugby league player]
-
A.
typeOfAthlete
chosen
Indicates that one entity is an athlete and the other specifies the kind or category of athlete they are.
-
B.
typeOfSportOfficial
Indicates that one entity serves as the specific role or type of sports official (e.g., referee, umpire, judge) associated with another entity.
-
C.
sportsIdentity
Indicates that an entity’s identity, role, or affiliation is defined in the context of sports (e.g., as an athlete, team, or sports-related organization).
-
D.
performsAtSport
Indicates that an entity carries out or participates in an activity at a particular sport or sporting context.
-
E.
sportEventType
Indicates the specific kind or category of sport associated with a given sporting event.
- 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_69e0b4c40ad88190b81f77695366d328 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c1d12a9481909cce3711c1c2d9f8 |
completed | April 21, 2026, 12:16 a.m. |
| PD | Predicate disambiguation | batch_69e5c044d1108190b2b5d25de23f6401 |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 12:15 p.m.