Triple
T21880900
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barsha Heights |
E540274
|
entity |
| Predicate | targetResidentProfile |
P41733
|
FINISHED |
| Object | expatriate professionals |
—
|
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: expatriate professionals | Statement: [Barsha Heights, targetResidentProfile, expatriate professionals]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetResidentProfile Context triple: [Barsha Heights, targetResidentProfile, expatriate professionals]
-
A.
targetMemberProfile
Indicates that one entity is the specific member profile that is the focus or destination of another entity’s action or reference.
-
B.
residentialProfile
Indicates the relationship between an entity and the characteristics or status of where and how it resides or is housed.
-
C.
participantProfile
Indicates that an entity serves as the profile or descriptive record associated with a particular participant in an event, activity, or process.
-
D.
profileType
Indicates the specific category or role classification assigned to a profile within a system.
-
E.
typicalProfile
chosen
Indicates that an entity represents the standard or most representative profile or pattern for another 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_69e0c479a98081908ce333853fdd4348 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f118e7a3c48190be1cc285ad4b6496 |
completed | April 28, 2026, 8:30 p.m. |
| PD | Predicate disambiguation | batch_69e6be9394f88190945ddd1dc004d29d |
completed | April 21, 2026, 12:02 a.m. |
Created at: April 16, 2026, 7:04 p.m.