Triple
T13851061
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NWSL Goalkeeper of the Year |
E332940
|
entity |
| Predicate | evaluationCriteriaIncludes |
P36515
|
FINISHED |
| Object | shot-stopping performance |
—
|
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: shot-stopping performance | Statement: [NWSL Goalkeeper of the Year, evaluationCriteriaIncludes, shot-stopping performance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: evaluationCriteriaIncludes Context triple: [NWSL Goalkeeper of the Year, evaluationCriteriaIncludes, shot-stopping performance]
-
A.
evaluationCriteriaInclude
chosen
Indicates that certain criteria are part of, or explicitly included in, the set of standards used to evaluate something.
-
B.
legalCriteriaInclude
Indicates that certain legal criteria are contained within, or form part of, a broader set of legal requirements or conditions.
-
C.
qualifyingFeaturesInclude
Indicates that certain qualifying features are part of, or included within, a specified set of features associated with an entity or condition.
-
D.
hasQualityCriterion
Indicates that something is associated with a specific standard or criterion used to judge its quality.
-
E.
compositionCriterion
Indicates the rule or standard by which components are selected, combined, or arranged to form a whole.
- 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_69d81c5ba13c8190839315f54768acfd |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de02d8fb788190baef7537be2baecb |
completed | April 14, 2026, 9:03 a.m. |
| PD | Predicate disambiguation | batch_69dbc8691b608190a25a7c70a366b170 |
completed | April 12, 2026, 4:29 p.m. |
Created at: April 9, 2026, 10:14 p.m.