Triple
T18566147
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IFRS 15 Revenue from Contracts with Customers |
E453764
|
entity |
| Predicate | stepOfModel |
P132547
|
FINISHED |
| Object | Identify the contract with a customer |
—
|
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: Identify the contract with a customer | Statement: [IFRS 15 Revenue from Contracts with Customers, stepOfModel, Identify the contract with a customer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stepOfModel Context triple: [IFRS 15 Revenue from Contracts with Customers, stepOfModel, Identify the contract with a customer]
-
A.
stepType
Indicates the specific kind or category of step an entity represents within a process or sequence.
-
B.
stepTakes
Indicates that one step directly follows or is taken after another step in a process or sequence.
-
C.
stepReturns
Indicates that a particular step in a process or workflow yields, outputs, or hands back a specified result or value.
-
D.
stepInRoutine
Indicates that an action or event occurs as an ordered step within a larger, structured routine or sequence of activities.
-
E.
stepUpdateType
Indicates the type or category of update applied to a particular step within a process or workflow.
- F. None of above. chosen
Provenance (4 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_69d8d38974308190a9174430ef256b73 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e53afe3ee081909eeee62c889948f4 |
completed | April 19, 2026, 8:28 p.m. |
| PD | Predicate disambiguation | batch_69e478c16e0c8190b03966aa23c395a6 |
completed | April 19, 2026, 6:40 a.m. |
| PDg | Predicate description generation | batch_69e484121cd48190bf583b4c94636a30 |
completed | April 19, 2026, 7:28 a.m. |
Created at: April 10, 2026, 11:43 a.m.