Triple
T4134588
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NIFL Premiership |
E85121
|
entity |
| Predicate | tierInUEFASystem |
P27406
|
FINISHED |
| Object | domestic top division |
—
|
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: domestic top division | Statement: [NIFL Premiership, tierInUEFASystem, domestic top division]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tierInUEFASystem Context triple: [NIFL Premiership, tierInUEFASystem, domestic top division]
-
A.
levelInUEFASystem
chosen
Indicates the specific tier or division an entity occupies within the hierarchical structure of the UEFA football league system.
-
B.
tierInNationalFootball
Indicates the competitive level or division within a country's national football league system in which an entity (e.g., a club or team) participates.
-
C.
tierInLeagueSystem
Indicates the specific hierarchical level or division an entity occupies within an organized league system.
-
D.
countryLeagueSystem
Indicates that a particular league system operates within, or is associated with, a specific country.
-
E.
UEFAStadiumCategory
Indicates the classification of a stadium according to UEFA’s official stadium category standards and requirements.
- 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_69aed935ccd881909dc61f81bcdb7a78 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af03a0f3408190adba7a8513bd3d12 |
completed | March 9, 2026, 5:30 p.m. |
| PD | Predicate disambiguation | batch_69af01883b6c8190a482ead589a131a5 |
completed | March 9, 2026, 5:21 p.m. |
Created at: March 9, 2026, 3:43 p.m.