Triple
T6974573
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South African Premier Division |
E161683
|
entity |
| Predicate | matchResultTiebreaker |
P6631
|
FINISHED |
| Object | goal difference |
—
|
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: goal difference | Statement: [South African Premier Division, matchResultTiebreaker, goal difference]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: matchResultTiebreaker Context triple: [South African Premier Division, matchResultTiebreaker, goal difference]
-
A.
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.
-
B.
tiebreakerGameLoser
Indicates the player or team that lost a specific tiebreaker game used to resolve a tie in a competition or match.
-
C.
resultOfMatch
Indicates that one entity is the outcome or product produced by a particular match or matching event involving another entity.
-
D.
matchOf
Indicates that one entity is a specific match, counterpart, or corresponding instance of another entity within a defined context or set.
-
E.
matchResult
Indicates the outcome or final status produced by a particular match or game between participants.
- 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_69c68854a0d88190bc0bf82263f1afce |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6db3bda908190a10a91dc8d043ef1 |
completed | March 27, 2026, 7:32 p.m. |
| PD | Predicate disambiguation | batch_69c6d7c262508190a7708b3d9cf23d7c |
completed | March 27, 2026, 7:17 p.m. |
Created at: March 27, 2026, 2:30 p.m.