Triple
T18190541
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Institutional Securities |
E435520
|
entity |
| Predicate | clientFocus |
P23437
|
FINISHED |
| Object | institutional clients |
—
|
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: institutional clients | Statement: [Institutional Securities, clientFocus, institutional clients]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: clientFocus Context triple: [Institutional Securities, clientFocus, institutional clients]
-
A.
importFocus
Indicates that attention, priority, or emphasis is being brought into or concentrated on a particular entity or aspect.
-
B.
customerFocus
chosen
Indicates that one entity prioritizes understanding and meeting the needs, preferences, or satisfaction of another entity (typically a customer or client).
-
C.
focusesOn
Indicates that one entity directs its attention, effort, or primary activity toward another entity or specific subject.
-
D.
deviceFocus
Indicates that attention, control, or primary interaction is directed toward a particular device in a given context.
-
E.
canonicalFocus
Indicates that one entity is the primary or most representative focus or point of attention in relation to another entity.
- 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_69d8b90c7ec081909b4694ccecb449c6 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4e0cf0d7c81908ce0386c52ef601d |
completed | April 19, 2026, 2:03 p.m. |
| PD | Predicate disambiguation | batch_69e4331e92408190ad607ba4956a3897 |
completed | April 19, 2026, 1:42 a.m. |
Created at: April 10, 2026, 10:31 a.m.