Triple
T18600072
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IFRS 9 Financial Instruments |
E454594
|
entity |
| Predicate | replacedImpairmentModel |
P28535
|
FINISHED |
| Object | Incurred loss model under IAS 39 |
—
|
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: Incurred loss model under IAS 39 | Statement: [IFRS 9 Financial Instruments, replacedImpairmentModel, Incurred loss model under IAS 39]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: replacedImpairmentModel Context triple: [IFRS 9 Financial Instruments, replacedImpairmentModel, Incurred loss model under IAS 39]
-
A.
repairedIn
Indicates that an item or object underwent repair within a specified location or during a particular time period.
-
B.
replacedWhenDisabledBy
Indicates that when one entity becomes disabled or nonfunctional, it is substituted or taken over by another entity.
-
C.
replacedPartOf
Indicates that one entity has taken the place of another entity as a component or part within a larger whole.
-
D.
replacedStandard
chosen
Indicates that one standard has been superseded or taken the place of another standard.
-
E.
replacedStructureDamagedBy
Indicates that a structure which has been replaced is (or was) damaged by a specified agent, event, or condition.
- 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_69d8d38ae7e081908a98df1251842402 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5475018548190a2f497081af7ce55 |
completed | April 19, 2026, 9:21 p.m. |
| PD | Predicate disambiguation | batch_69e478cf5e888190a0b1074b0c6525df |
completed | April 19, 2026, 6:40 a.m. |
Created at: April 10, 2026, 11:45 a.m.