Triple
T5308787
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ginnie Mae |
E120168
|
entity |
| Predicate | doesNotBuy |
P4300
|
FINISHED |
| Object | mortgages |
—
|
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: mortgages | Statement: [Ginnie Mae, doesNotBuy, mortgages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: doesNotBuy Context triple: [Ginnie Mae, doesNotBuy, mortgages]
-
A.
doesNot
chosen
Indicates that a specified entity lacks, refrains from, or fails to perform a particular action or exhibit a particular property in relation to another entity or context.
-
B.
doesNotUse
Indicates that one entity intentionally refrains from employing, utilizing, or relying on another entity, method, or resource.
-
C.
doesNotAccept
Indicates that one entity refuses, rejects, or is not configured to receive or allow something from another entity.
-
D.
doesNotServe
Indicates that one entity explicitly does not provide a service, function, or role to another entity.
-
E.
doesNotConsider
Indicates that one entity fails or chooses not to take another entity or factor into account when forming judgments, decisions, or actions.
- 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_69bd44704be88190acdb2ac481b0ff55 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd86f20f008190be7b5848af05f2b8 |
completed | March 20, 2026, 5:42 p.m. |
| PD | Predicate disambiguation | batch_69bd84534f9c8190bc19d4812060768d |
completed | March 20, 2026, 5:30 p.m. |
Created at: March 20, 2026, 1:53 p.m.