Triple
T31661014
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mid Canterbury Rugby Football Union |
E807999
|
entity |
| Predicate | typeOfTeamStructure |
P2705
|
FINISHED |
| Object | amateur and semi-professional |
—
|
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: amateur and semi-professional | Statement: [Mid Canterbury Rugby Football Union, typeOfTeamStructure, amateur and semi-professional]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfTeamStructure Context triple: [Mid Canterbury Rugby Football Union, typeOfTeamStructure, amateur and semi-professional]
-
A.
typeOfTeams
chosen
Indicates the categories or kinds of teams to which an entity or group of entities belongs.
-
B.
hasTeamStructure
Indicates that an entity is organized into, or associated with, a specific arrangement of teams or team hierarchy.
-
C.
teamNumberType
Indicates the type or category assigned to a team’s identifying number within a given system or context.
-
D.
organizingStructure
Indicates that one entity serves as the framework or arrangement that orders, coordinates, or structures another entity or set of entities.
-
E.
teamCountType
Indicates how the number of teams is categorized or measured within a given 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_69f348daf95c81908b4c985b7ddcd0b3 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69fffc783b648190bcd7df017514d206 |
completed | May 10, 2026, 3:33 a.m. |
| PD | Predicate disambiguation | batch_69fffc03fa24819099e12413dc6e0afd |
completed | May 10, 2026, 3:31 a.m. |
Created at: April 30, 2026, 10:57 p.m.