Triple
T23249776
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BPI Bronze (single) |
E581699
|
entity |
| Predicate | hasMinimumRequirementType |
P36473
|
FINISHED |
| Object | threshold of sales or streams |
—
|
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: threshold of sales or streams | Statement: [BPI Bronze (single), hasMinimumRequirementType, threshold of sales or streams]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMinimumRequirementType Context triple: [BPI Bronze (single), hasMinimumRequirementType, threshold of sales or streams]
-
A.
hasMinimum
Indicates that an entity possesses at least a specified lower bound or smallest allowable value, quantity, or level in relation to another entity or constraint.
-
B.
hasEntryRequirement
chosen
Indicates that one entity specifies conditions or qualifications that must be met before another entity is allowed access, participation, or admission.
-
C.
hasMinimumWeight
Indicates that an entity’s weight meets or exceeds a specified minimum threshold.
-
D.
hasMinimumSize
Indicates that an entity meets or exceeds a specified minimum size threshold.
-
E.
hasCapType
Indicates that an entity possesses or is characterized by a specific type of cap or cap-like feature.
- 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_69e24606b17c81908aba1a4911c8a8ba |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f193f4d7e4819085eec6279696db34 |
completed | April 29, 2026, 5:15 a.m. |
| PD | Predicate disambiguation | batch_69effce4d704819092826931d430e8c4 |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:10 p.m.