Triple
T7888192
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caroline Gomes |
E183156
|
entity |
| Predicate | ethnicGroupAdvocacy |
P73983
|
FINISHED |
| Object | marginalized groups in Brazil |
—
|
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: marginalized groups in Brazil | Statement: [Caroline Gomes, ethnicGroupAdvocacy, marginalized groups in Brazil]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ethnicGroupAdvocacy Context triple: [Caroline Gomes, ethnicGroupAdvocacy, marginalized groups in Brazil]
-
A.
ethnicGroupAdvocatedFor
chosen
Indicates that one entity actively supported, promoted, or defended the interests or rights of a particular ethnic group.
-
B.
advocacyOrganization
Indicates that an organization actively supports, promotes, or works on behalf of a cause, issue, or group through advocacy activities.
-
C.
ethnicGroupHelped
Indicates that one ethnic group provided assistance or support to another entity or group.
-
D.
ethnicGroupConfronted
Indicates that one ethnic group has faced opposition, conflict, or hostile interaction from another group or entity.
-
E.
advocatesAgainst
Indicates that one entity actively opposes, argues against, or campaigns to prevent or stop another entity, action, or idea.
- 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_69ca828af6e48190a06ee7010d8f0e64 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb39ea8d1c81908ef99569e0cf00b7 |
completed | March 31, 2026, 3:05 a.m. |
| PD | Predicate disambiguation | batch_69cae92b0cd881908e715a10d3252e83 |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 4:59 p.m.