Triple
T22764817
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Egyptian interbank market |
E563092
|
entity |
| Predicate | liquiditySourceFor |
P65105
|
FINISHED |
| Object | Egyptian banking sector |
—
|
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: Egyptian banking sector | Statement: [Egyptian interbank market, liquiditySourceFor, Egyptian banking sector]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: liquiditySourceFor Context triple: [Egyptian interbank market, liquiditySourceFor, Egyptian banking sector]
-
A.
liquidityScreening
Indicates that an entity is evaluated or filtered based on its ability to meet short-term financial obligations or convert assets to cash (i.e., its liquidity).
-
B.
hasLiquidityCharacteristic
Indicates that one entity possesses or is associated with a particular liquidity-related property or feature in relation to another entity.
-
C.
qualifyingSource
Indicates that one entity serves as the source or basis that provides the necessary conditions or qualifications for another entity or statement.
-
D.
sourceOfCapital
chosen
Indicates the origin or provider from which an entity obtains its financial capital or funding.
-
E.
distributorOfSource
Indicates that one entity acts as the distributor or provider of a particular source, making that source available to others.
- 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_69e24552e11c81909c2d61578a558bd7 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17a7f56848190b5e90f9916a5b349 |
completed | April 29, 2026, 3:26 a.m. |
| PD | Predicate disambiguation | batch_69eed2b88d88819096015deb6a648801 |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:26 p.m.