Triple
T17677456
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FDR model checker |
E440674
|
entity |
| Predicate | checksRelation |
P127964
|
FINISHED |
| Object | implementation refines specification |
—
|
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: implementation refines specification | Statement: [FDR model checker, checksRelation, implementation refines specification]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: checksRelation Context triple: [FDR model checker, checksRelation, implementation refines specification]
-
A.
testsRelation
chosen
Indicates a relationship where one entity evaluates, examines, or verifies another entity, typically to assess its properties, behavior, or correctness.
-
B.
hasRelation
Indicates that there exists some specified relationship or association between two entities.
-
C.
supportsRelation
Indicates that one entity provides assistance, endorsement, or structural backing to another entity or its activity.
-
D.
valueRelation
Indicates a comparative or associative relationship between the values or magnitudes of two or more entities.
-
E.
stepRelation
Indicates a relationship where one entity is a step-relative of another, such as a stepparent, stepchild, or stepsibling connection.
- 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_69d8b9e940b081908b862bb0e6e89b0d |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e46f6e959c819092d9d33e79bd51f7 |
completed | April 19, 2026, 6 a.m. |
| PD | Predicate disambiguation | batch_69e3cde3673c8190a889e14ba1f07dc1 |
completed | April 18, 2026, 6:30 p.m. |
Created at: April 10, 2026, 10:01 a.m.