Triple
T17450290
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Soviet Second League |
E424894
|
entity |
| Predicate | levelRelativeToTop |
P102229
|
FINISHED |
| Object | two levels below Soviet Top League |
—
|
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: two levels below Soviet Top League | Statement: [Soviet Second League, levelRelativeToTop, two levels below Soviet Top League]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: levelRelativeToTop Context triple: [Soviet Second League, levelRelativeToTop, two levels below Soviet Top League]
-
A.
positionRelativeToTopFlight
chosen
Indicates the relative vertical placement of something with respect to the topmost flight (e.g., of stairs or levels).
-
B.
relativeLevel
Indicates a comparative relationship specifying how one entity’s level, degree, or intensity of some property stands relative to that of another entity.
-
C.
topLevelOf
Indicates that one entity is the highest or most overarching level within the structure or hierarchy of another entity.
-
D.
leafPosition
Indicates the spatial or structural placement of a leaf relative to its supporting plant organ or axis.
-
E.
levelStructure
Indicates that one entity defines or organizes the hierarchical or layered arrangement of another entity.
- 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_69d889db0ba481908402409af3b37917 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4513d00f48190802a3bdc8c8f4db5 |
completed | April 19, 2026, 3:51 a.m. |
| PD | Predicate disambiguation | batch_69e3b4f0e3fc819094e466b74622c956 |
completed | April 18, 2026, 4:44 p.m. |
Created at: April 10, 2026, 5:47 a.m.