Triple
T23938245
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Admiral Capital Group |
E602701
|
entity |
| Predicate | hasImpactOrientation |
P74556
|
FINISHED |
| Object | social impact investing |
—
|
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: social impact investing | Statement: [Admiral Capital Group, hasImpactOrientation, social impact investing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasImpactOrientation Context triple: [Admiral Capital Group, hasImpactOrientation, social impact investing]
-
A.
hasOrientation
Indicates that one entity is positioned or directed in a specific spatial or conceptual alignment relative to a reference frame or another entity.
-
B.
orientationInducedBy
Indicates that the orientation of one entity is determined or caused by the orientation or configuration of another entity.
-
C.
hasVisualImpact
Indicates that one entity affects or influences the visual appearance or aesthetic perception of another.
-
D.
orientationType
Indicates the specific kind or category of orientation relationship that exists between entities (such as spatial, directional, or alignment-based orientation).
-
E.
hasImpactFocus
chosen
Indicates that an entity is primarily concerned with or directed toward a particular type or area of impact.
- 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_69e2953cf6e081909b8e25a10a52dddc |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1cfa267b88190a1e7d599f22441e2 |
completed | April 29, 2026, 9:30 a.m. |
| PD | Predicate disambiguation | batch_69f1615518088190a206f54e2fdb14a3 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:07 p.m.