Triple
T10566374
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Supercopa Sudamericana |
E249358
|
entity |
| Predicate | typeOfKnockout |
P4224
|
FINISHED |
| Object | two-legged ties with aggregate score |
—
|
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-legged ties with aggregate score | Statement: [Supercopa Sudamericana, typeOfKnockout, two-legged ties with aggregate score]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfKnockout Context triple: [Supercopa Sudamericana, typeOfKnockout, two-legged ties with aggregate score]
-
A.
knockoutNature
Indicates that one entity causes another to be eliminated, disabled, or rendered nonfunctional, typically in a decisive or forceful manner.
-
B.
typeOf
chosen
Indicates that one entity is a specific kind, class, or category instance of another more general entity.
-
C.
hasKnockoutRule
Indicates that a rule or condition exists specifying when and how a knockout (elimination) occurs in a competitive or game-like setting.
-
D.
typeOfHit
Indicates the specific category or kind of hit or strike that occurred in an interaction or event.
-
E.
typeOfControl
Indicates the specific manner or mechanism by which one entity exercises control or influence over another.
- 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_69d381c8bd708190acf3d275c908251e |
completed | April 6, 2026, 9:50 a.m. |
| NER | Named-entity recognition | batch_69d5272ce78c8190bf3227053ef88a48 |
completed | April 7, 2026, 3:47 p.m. |
| PD | Predicate disambiguation | batch_69d51901ff6c819095e7b528170a69dc |
completed | April 7, 2026, 2:47 p.m. |
Created at: April 6, 2026, 12:36 p.m.