Triple
T1137001
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Office of Housing |
E23162
|
entity |
| Predicate | usesProgramType |
P2192
|
FINISHED |
| Object | mortgage insurance |
—
|
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 insurance | Statement: [Office of Housing, usesProgramType, mortgage insurance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesProgramType Context triple: [Office of Housing, usesProgramType, mortgage insurance]
-
A.
usedProgramModel
Indicates that an entity employed a specific program model as the basis or framework for its activities or operations.
-
B.
programType
chosen
Indicates the category or kind of program to which an entity belongs or with which it is associated.
-
C.
programUsed
Indicates that a particular program, software, or application was employed or utilized in performing an action or achieving a result.
-
D.
hasProgramCode
Indicates that an entity is associated with a specific program identifier or code used to reference or classify it within a system.
-
E.
implementedProgram
Indicates that an entity has created, developed, or put into operation a particular program or software system.
- 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_69a493ec75988190b63a11bafaec29b4 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4bde18d208190848c189b2b8d585f |
completed | March 1, 2026, 10:29 p.m. |
| PD | Predicate disambiguation | batch_69a4bb4b52d48190bec2e7ad1cc8efc0 |
completed | March 1, 2026, 10:18 p.m. |
Created at: March 1, 2026, 7:44 p.m.