Triple
T9630827
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hamburg derby |
E232797
|
entity |
| Predicate | securityRiskLevel |
P3842
|
FINISHED |
| Object | high-risk match classification |
—
|
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: high-risk match classification | Statement: [Hamburg derby, securityRiskLevel, high-risk match classification]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: securityRiskLevel Context triple: [Hamburg derby, securityRiskLevel, high-risk match classification]
-
A.
riskLevel
chosen
Indicates the degree of potential harm, loss, or adverse outcome associated with a particular situation, action, or entity.
-
B.
riskType
Indicates the category or nature of risk associated with an entity, event, or relationship.
-
C.
securityLevelDetail
Indicates the specific classification or degree of security associated with an entity, often including nuanced or descriptive information about its protection level.
-
D.
riskGroup
Indicates that an entity belongs to a category of individuals or items that share an elevated level of risk relative to others.
-
E.
riskElement
Indicates that one entity is a risk-related component, factor, or contributor associated with another entity within a risk context.
- 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_69ca848940cc8190b97cec654cb3bb4a |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9b2621408190bfe2ea5a05359ee0 |
completed | April 1, 2026, 10:24 p.m. |
| PD | Predicate disambiguation | batch_69ccd5acfa5c8190aaba3cf548723604 |
completed | April 1, 2026, 8:22 a.m. |
Created at: March 30, 2026, 8:11 p.m.