Triple
T15957495
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Afro-Asian Club Championship |
E386972
|
entity |
| Predicate | deciderIfStillTied |
P6631
|
FINISHED |
| Object | penalty shoot-out |
—
|
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: penalty shoot-out | Statement: [Afro-Asian Club Championship, deciderIfStillTied, penalty shoot-out]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: deciderIfStillTied Context triple: [Afro-Asian Club Championship, deciderIfStillTied, penalty shoot-out]
-
A.
hasTieGame
Indicates that a game or match has ended with both sides having the same score, resulting in no winner.
-
B.
maintainsTieWith
Indicates that one entity keeps an ongoing connection or relationship with another entity over time.
-
C.
decidingGameWinner
Indicates that an event, action, or process determines which participant is the winner of a game.
-
D.
tiebreaker
chosen
Indicates that one entity serves as the deciding factor used to break a tie between two or more otherwise equal options or outcomes.
-
E.
hasTiePossibility
Indicates that a situation, event, or interaction has the potential to end in a tie or draw rather than producing a single winner.
- 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_69d86da882448190a82ea962fe343b79 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e17d4d08f481909f38b75e3f42d9ab |
completed | April 17, 2026, 12:22 a.m. |
| PD | Predicate disambiguation | batch_69e142d37cd88190ab50760f1783e20c |
completed | April 16, 2026, 8:13 p.m. |
Created at: April 10, 2026, 4:53 a.m.