Triple
T31268731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grupo Danhos |
E797323
|
entity |
| Predicate | propertyPortfolioType |
P149833
|
FINISHED |
| Object | income-generating properties |
—
|
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: income-generating properties | Statement: [Grupo Danhos, propertyPortfolioType, income-generating properties]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: propertyPortfolioType Context triple: [Grupo Danhos, propertyPortfolioType, income-generating properties]
-
A.
propertyTypeOwned
Indicates that one entity owns a specific type or category of property in relation to another entity.
-
B.
propertyType_id
chosen
Indicates a relationship that specifies the type or category of a property associated with an entity.
-
C.
propertyType_rid
Indicates that an entity is associated with a specific property type identified by a unique resource identifier (RID).
-
D.
propertyTypeOf
Indicates that one entity is the type or category of property to which another entity belongs.
-
E.
propertyHeld
Indicates that a particular property is possessed, owned, or controlled by a specified 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_69f224de2bbc819081af6c32e1d857b9 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6c8159edc8190b1c87015e0c820e8 |
completed | May 3, 2026, 3:59 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f42fbc8190a06eb1044c9e6094 |
completed | May 3, 2026, 3:41 a.m. |
Created at: April 29, 2026, 9:13 p.m.