Triple
T1082950
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NDX |
E23986
|
entity |
| Predicate | sectorExclusion |
P3119
|
FINISHED |
| Object | traditional financial companies such as banks and insurers |
—
|
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: traditional financial companies such as banks and insurers | Statement: [NDX, sectorExclusion, traditional financial companies such as banks and insurers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sectorExclusion Context triple: [NDX, sectorExclusion, traditional financial companies such as banks and insurers]
-
A.
excludes
chosen
Indicates that one entity deliberately omits, leaves out, or does not allow the inclusion of another entity within a set, group, or context.
-
B.
excludesRegion
Indicates that one entity explicitly omits, leaves out, or does not apply to a specified region or geographic area.
-
C.
acquisitionExcludes
Indicates that a particular acquisition explicitly does not include certain entities, assets, or rights within its scope.
-
D.
sectorProtected
Indicates that a particular sector or area is safeguarded from harm, access, or exploitation by some form of protection or regulation.
-
E.
isSectorSpecific
Indicates that something is tailored or restricted to a particular industry or sector rather than being generally applicable.
- 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_69a493f1ddf48190a99d54b00e99f8ce |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b95e56948190a1e92367ad7240b7 |
completed | March 1, 2026, 10:10 p.m. |
| PD | Predicate disambiguation | batch_69a4b73f4310819086281f8ec67d1a32 |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:42 p.m.