Triple
T2132983
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MLS Cup 2021 |
E46583
|
entity |
| Predicate | equalizingGoalMinute |
P7494
|
FINISHED |
| Object | 90+4 |
—
|
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: 90+4 | Statement: [MLS Cup 2021, equalizingGoalMinute, 90+4]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: equalizingGoalMinute Context triple: [MLS Cup 2021, equalizingGoalMinute, 90+4]
-
A.
equalizingGoalBy
Indicates that one entity has the objective of reducing differences or disparities between itself and another entity.
-
B.
decidingGoalMinute
chosen
Indicates the minute in a match when a goal is scored that ultimately decides the outcome (e.g., the winning or decisive goal).
-
C.
numberOfGoals
Indicates the total count of goals scored or achieved by an entity in a given context.
-
D.
averageGoalsPerMatch
Indicates the typical number of goals scored per match in the context of the given entities or competition.
-
E.
ownGoalBy
Indicates that a goal was accidentally scored against a team by the specified player (i.e., the player scored an own goal).
- 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_69a88a1626548190ae59a5028c3baa8e |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abbba0c42c8190ab3ce4bbf1531ee1 |
completed | March 7, 2026, 5:46 a.m. |
| PD | Predicate disambiguation | batch_69abb7bf56e481909b0f497d238451cc |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:44 p.m.