Triple
T4134576
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NIFL Premiership |
E85121
|
entity |
| Predicate | matchOutcomeTiebreaker |
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: [NIFL Premiership, matchOutcomeTiebreaker, goal difference]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: matchOutcomeTiebreaker Context triple: [NIFL Premiership, matchOutcomeTiebreaker, 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.
finalMatchType
Indicates the specific category or format of the concluding or decisive match in a series or competition.
-
C.
hasTieGame
Indicates that a game or match has ended with both sides having the same score, resulting in no winner.
-
D.
matchOf
Indicates that one entity is a specific match, counterpart, or corresponding instance of another entity within a defined context or set.
-
E.
featuredMatchWinner
Indicates that an entity is the winner of a highlighted or prominently featured match.
- 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_69aed935ccd881909dc61f81bcdb7a78 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af03a0f3408190adba7a8513bd3d12 |
completed | March 9, 2026, 5:30 p.m. |
| PD | Predicate disambiguation | batch_69af01883b6c8190a482ead589a131a5 |
completed | March 9, 2026, 5:21 p.m. |
Created at: March 9, 2026, 3:43 p.m.