Triple
T18506524
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Net Promoter Score |
E452210
|
entity |
| Predicate | calculatedAs |
P24421
|
FINISHED |
| Object | percentage of Promoters minus percentage of Detractors |
—
|
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: percentage of Promoters minus percentage of Detractors | Statement: [Net Promoter Score, calculatedAs, percentage of Promoters minus percentage of Detractors]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: calculatedAs Context triple: [Net Promoter Score, calculatedAs, percentage of Promoters minus percentage of Detractors]
-
A.
calculatedOn
Indicates that a value, result, or outcome is computed based on or using the referenced entity as its input, basis, or context.
-
B.
calculated
Indicates that one entity has determined or computed a value, result, or outcome based on information from another entity.
-
C.
calculationProvider
Indicates that one entity serves as the source or performer of a calculation for another entity or process.
-
D.
calculationType
chosen
Indicates the specific method, formula, or approach used to perform a calculation in the described relationship.
-
E.
isCalculatedInRealTime
Indicates that the value or result is computed dynamically at the moment of use rather than being precomputed or stored.
- 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_69d8d386df84819092355ebb260d848e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5334266708190b59aca3a2218c095 |
completed | April 19, 2026, 7:55 p.m. |
| PD | Predicate disambiguation | batch_69e469dbf5208190b6fc49e02a087f54 |
completed | April 19, 2026, 5:36 a.m. |
Created at: April 10, 2026, 11:36 a.m.