Triple
T3100545
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Trump Management |
E64704
|
entity |
| Predicate | propertyTypeManaged |
P27844
|
FINISHED |
| Object | subsidized housing |
—
|
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: subsidized housing | Statement: [Trump Management, propertyTypeManaged, subsidized housing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: propertyTypeManaged Context triple: [Trump Management, propertyTypeManaged, subsidized housing]
-
A.
propertyTypeOwned
chosen
Indicates that one entity owns a specific type or category of property in relation to another entity.
-
B.
ownedProperty
Indicates that one entity possesses legal ownership or control over another entity as property.
-
C.
propertyTypeMix
Indicates that an entity involves or consists of a combination of different types of properties rather than a single uniform property type.
-
D.
numberOfPropertiesManaged
Indicates the total count of properties that an entity is responsible for managing.
-
E.
architectureProperty
Indicates that a specified architectural characteristic or feature is attributed to, or associated with, an entity.
- 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_69ad857dc98481909e585dc3372e3ed5 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada26b03a081909cf187b9a8f805ce |
completed | March 8, 2026, 4:23 p.m. |
| PD | Predicate disambiguation | batch_69ad9df06ed88190809f0683122caa5a |
completed | March 8, 2026, 4:04 p.m. |
Created at: March 8, 2026, 3:03 p.m.