Triple
T5490967
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Star Island |
E123698
|
entity |
| Predicate | primaryPropertyType |
P542
|
FINISHED |
| Object | single-family homes |
—
|
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: single-family homes | Statement: [Star Island, primaryPropertyType, single-family homes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryPropertyType Context triple: [Star Island, primaryPropertyType, single-family homes]
-
A.
residenceType
chosen
Indicates the kind or category of dwelling or living arrangement associated with an entity.
-
B.
propertyTypeOwned
Indicates that one entity owns a specific type or category of property in relation to another entity.
-
C.
primaryListing
Indicates that one item in a set of listings is designated as the main or most authoritative listing for a given entity or context.
-
D.
property
Indicates that one entity possesses, is characterized by, or has an attribute or quality associated with another entity.
-
E.
realEstateCategory
Indicates the classification of a property into a specific type or category within real estate (e.g., residential, commercial, industrial).
- 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_69bd464a2d908190869324ce176779c8 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd927f198c8190889b555be9bf9765 |
completed | March 20, 2026, 6:31 p.m. |
| PD | Predicate disambiguation | batch_69bd91a8df6481908d1643f7342fe6f0 |
completed | March 20, 2026, 6:27 p.m. |
Created at: March 20, 2026, 2:10 p.m.