Triple
T7518683
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MLS Cup 2023 |
E177709
|
entity |
| Predicate | previousEdition |
P97
|
FINISHED |
| Object | MLS Cup 2022 |
E83259
|
NE 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: MLS Cup 2022 | Statement: [MLS Cup 2023, previousEdition, MLS Cup 2022]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MLS Cup 2022 Context triple: [MLS Cup 2023, previousEdition, MLS Cup 2022]
-
A.
MLS Cup 2022
chosen
MLS Cup 2022 was the championship match of Major League Soccer’s 2022 season, determining the league’s overall champion through a postseason final.
-
B.
MLS Cup 2023
MLS Cup 2023 was the championship match of Major League Soccer’s 2023 season, culminating in Columbus Crew being crowned league champions.
-
C.
MLS Cup 2021
MLS Cup 2021 was the Major League Soccer championship match in which New York City FC secured their first league title.
-
D.
MLS Cup 2020
MLS Cup 2020 was the championship match of Major League Soccer’s 2020 season, determining the league’s overall title winner in a year heavily impacted by the COVID-19 pandemic.
-
E.
MLS Cup 2019
MLS Cup 2019 was the championship match of the 2019 Major League Soccer season, serving as the league’s title-deciding game.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c69f2891148190a484f3b8222c6f1b |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f5f850c081909e697219071293fc |
completed | March 27, 2026, 9:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8462610b481909fa74023852b0154 |
completed | March 28, 2026, 9:20 p.m. |
Created at: March 27, 2026, 3:46 p.m.