Triple
T19523622
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Latvian Higher League |
E488463
|
entity |
| Predicate | hasSubsequentStage |
P47020
|
FINISHED |
| Object | European competition qualifiers for top clubs |
—
|
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: European competition qualifiers for top clubs | Statement: [Latvian Higher League, hasSubsequentStage, European competition qualifiers for top clubs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSubsequentStage Context triple: [Latvian Higher League, hasSubsequentStage, European competition qualifiers for top clubs]
-
A.
hasSubsequent
chosen
Indicates that one entity occurs, appears, or is positioned after another in a defined sequence or order.
-
B.
hasSubsequentWork
Indicates that one work is followed by another work that continues, succeeds, or builds upon it in sequence.
-
C.
hasSubsequentStandard
Indicates that one standard is followed or superseded by another standard that comes after it in sequence or version.
-
D.
hasFinalStage
Indicates that an entity possesses or reaches a concluding or ultimate phase in a process, sequence, or lifecycle.
-
E.
hasSuccessorSegment
Indicates that one segment directly follows another segment in a sequence or ordered structure.
- 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_69d8e8da8bec819081f400199491ccc3 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e636392444819094f6a2aa1cdf3d42 |
completed | April 20, 2026, 2:20 p.m. |
| PD | Predicate disambiguation | batch_69e514c9c00481909b76bda67957e58b |
completed | April 19, 2026, 5:45 p.m. |
Created at: April 10, 2026, 1:41 p.m.