Triple
T6974574
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South African Premier Division |
E161683
|
entity |
| Predicate | secondaryTiebreaker |
P21576
|
FINISHED |
| Object | goals scored |
—
|
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: goals scored | Statement: [South African Premier Division, secondaryTiebreaker, goals scored]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secondaryTiebreaker Context triple: [South African Premier Division, secondaryTiebreaker, goals scored]
-
A.
secondaryTo
Indicates that one condition, event, or factor occurs as a consequence of, or is caused by, another primary condition, event, or factor.
-
B.
secondTier
Indicates that something occupies a secondary or subordinate level of importance, quality, or rank relative to a primary or top tier.
-
C.
secondRunnerUp
Indicates that one entity finished in third place in a competition or ranking relative to the others.
-
D.
secondaryMetric
chosen
Indicates that one metric serves as an additional, supporting measure used alongside a primary metric for evaluation or analysis.
-
E.
secondaryCompetition
Indicates that one entity participates in or is involved with a secondary or subordinate competition relative to a primary one.
- 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.