Triple
T6611124
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FA Women's Cup |
E149238
|
entity |
| Predicate | knockoutTieResolution |
P40473
|
FINISHED |
| Object | single-leg ties |
—
|
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: single-leg ties | Statement: [FA Women's Cup, knockoutTieResolution, single-leg ties]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: knockoutTieResolution Context triple: [FA Women's Cup, knockoutTieResolution, single-leg ties]
-
A.
tiebreaker
Indicates that one entity serves as the deciding factor used to break a tie between two or more otherwise equal options or outcomes.
-
B.
knockoutNature
Indicates that one entity causes another to be eliminated, disabled, or rendered nonfunctional, typically in a decisive or forceful manner.
-
C.
maintainsTieWith
Indicates that one entity keeps an ongoing connection or relationship with another entity over time.
-
D.
resolutionMethod
Indicates the specific approach, technique, or process used to resolve a problem, conflict, or issue.
-
E.
hasKnockoutRule
chosen
Indicates that a rule or condition exists specifying when and how a knockout (elimination) occurs in a competitive or game-like setting.
- 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_69c687ebc680819094caf71faba2efe2 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6cf3796d08190a26e988386089447 |
completed | March 27, 2026, 6:40 p.m. |
| PD | Predicate disambiguation | batch_69c6acfed25481909cac74c84a9fe088 |
completed | March 27, 2026, 4:14 p.m. |
Created at: March 27, 2026, 1:57 p.m.