Triple
T20808897
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | LDI |
E512241
|
entity |
| Predicate | hasIssuerSubsector |
P105701
|
FINISHED |
| Object | mortgage finance |
—
|
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: mortgage finance | Statement: [LDI, hasIssuerSubsector, mortgage finance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasIssuerSubsector Context triple: [LDI, hasIssuerSubsector, mortgage finance]
-
A.
hasIssuerPrimaryBusiness
Indicates that an entity’s main or primary line of business is identified or characterized by the associated business activity or classification.
-
B.
belongsToSubsector
chosen
Indicates that one entity is part of, or classified within, a more specific subsector of a broader sector or industry.
-
C.
typicalIssuer
Indicates that one entity is the standard or commonly expected issuer (e.g., of a document, instrument, or credential) for another entity.
-
D.
hasIssuerCode
Indicates that an entity is associated with a specific issuer’s identifying code.
-
E.
indicatesIssuer
Indicates that one entity serves as the issuer or originator of another entity, such as a document, credential, or financial instrument.
- 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_69e0b4cd25088190b48ca9700cd24efc |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2d199888190b8b190c928f510b7 |
completed | April 21, 2026, 12:20 a.m. |
| PD | Predicate disambiguation | batch_69e5c99ca55481908e8d434fa901cfd6 |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 12:40 p.m.