Triple
T5461484
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arora Punjabis |
E122602
|
entity |
| Predicate | diasporaOccupation |
P46161
|
FINISHED |
| Object | business |
—
|
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: business | Statement: [Arora Punjabis, diasporaOccupation, business]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: diasporaOccupation Context triple: [Arora Punjabis, diasporaOccupation, business]
-
A.
diasporaType
Indicates the specific kind or category of diaspora relationship that exists between a group and its place of origin.
-
B.
diasporaRole
chosen
Indicates the role, function, or capacity that a member of a diaspora community holds or performs in relation to their origin or host context.
-
C.
diasporaComponentOf
Indicates that one entity is a constituent or subgroup of the broader diaspora associated with another entity.
-
D.
diasporaCharacteristic
Indicates that an entity possesses a quality, feature, or attribute specifically associated with a diaspora community or condition.
-
E.
diasporaOrganization
Indicates that an organization is associated with, represents, or serves a diaspora community outside its ancestral or origin country.
- 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_69bd4643f16081908d7f29e08096115a |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd927c946c8190aef40679199fede3 |
completed | March 20, 2026, 6:31 p.m. |
| PD | Predicate disambiguation | batch_69bd91a370a88190b5d17b8a5387138d |
completed | March 20, 2026, 6:27 p.m. |
Created at: March 20, 2026, 2:08 p.m.