Triple
T27961964
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cadorna FN |
E704600
|
entity |
| Predicate | codeForOperator |
P38995
|
FINISHED |
| Object | Ferrovie Nord Milano network |
—
|
NE NERFINISHED |
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: Ferrovie Nord Milano network | Statement: [Cadorna FN, codeForOperator, Ferrovie Nord Milano network]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: codeForOperator Context triple: [Cadorna FN, codeForOperator, Ferrovie Nord Milano network]
-
A.
operatorCode
chosen
Indicates that one entity is associated with a specific operator’s identifying code used to denote who performs or manages an operation or service.
-
B.
codeFor
Indicates that one entity serves as the implementation, encoding, or programmatic representation for another entity.
-
C.
codeForLanguage
Indicates that a piece of code is written in, or intended to be executed by, a particular programming or markup language.
-
D.
operatorBase
Indicates that one entity serves as the primary or foundational operator for another entity or operation.
-
E.
operatorVariant
Indicates a relationship where one operator is an alternative or modified form of another, typically differing in implementation, configuration, or usage while serving a related function.
- 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_69ef841061e48190b5570f9562f7434d |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_69f63b0414388190a2a2c5c237bd4dc4 |
completed | May 2, 2026, 5:57 p.m. |
| PD | Predicate disambiguation | batch_69f63710d17c819084cfe96e6df334fd |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 27, 2026, 7:32 p.m.