Triple
T7518686
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MLS Cup 2023 |
E177709
|
entity |
| Predicate | qualificationMethodOfHost |
P77434
|
FINISHED |
| Object | better regular-season record among finalists |
—
|
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: better regular-season record among finalists | Statement: [MLS Cup 2023, qualificationMethodOfHost, better regular-season record among finalists]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: qualificationMethodOfHost Context triple: [MLS Cup 2023, qualificationMethodOfHost, better regular-season record among finalists]
-
A.
hostCitySelectionMethod
Indicates the process or criteria by which a host city is chosen for an event or activity.
-
B.
hostCountrySelectionMethod
Indicates the process or criteria by which a host country is chosen for an event, program, or activity.
-
C.
mayHost
Indicates that an entity is permitted or able to serve as the location or organizer for another entity or event.
-
D.
judgesSelectionMethod
Indicates that a judge or judging body uses a particular method or criteria to evaluate and select among options or candidates.
-
E.
typicalHostSelection
Indicates the usual or preferred choice of host entity that is selected in a given context or process.
- F. None of above. chosen
Provenance (4 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. |
| PD | Predicate disambiguation | batch_69c6f4d44e9481909813e073b194f6f4 |
completed | March 27, 2026, 9:21 p.m. |
| PDg | Predicate description generation | batch_69c6f574d8a8819095749518dad13791 |
completed | March 27, 2026, 9:24 p.m. |
Created at: March 27, 2026, 3:46 p.m.