Triple
T37219194
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Commissioner Bele |
E922827
|
entity |
| Predicate | prejudiceBasedOn |
P164405
|
FINISHED |
| Object | skin color orientation |
—
|
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: skin color orientation | Statement: [Commissioner Bele, prejudiceBasedOn, skin color orientation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: prejudiceBasedOn Context triple: [Commissioner Bele, prejudiceBasedOn, skin color orientation]
-
A.
prejudiceStandard
Indicates that one entity applies a biased or pre-judged standard or criterion when evaluating or treating another entity.
-
B.
discriminatedAgainst
Indicates that one entity treats another unfairly or unequally based on a particular characteristic, such as race, gender, or other protected attributes.
-
C.
bias
Indicates a systematic preference or prejudice in favor of or against an entity, affecting how it is treated, evaluated, or represented relative to others.
-
D.
discriminationGround
chosen
Indicates the basis or reason (such as a characteristic or attribute) on which discriminatory treatment is applied in the relationship.
-
E.
prohibitsDiscriminationBasis
Indicates that an entity forbids discriminatory treatment based on specified characteristics or grounds.
- 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_69f76ea6f5288190b8d9988f613811c0 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb4134225081909fd60703b8cae397 |
completed | May 6, 2026, 1:25 p.m. |
| PD | Predicate disambiguation | batch_69fb35bf767081908de8345358ca7f44 |
completed | May 6, 2026, 12:36 p.m. |
Created at: May 3, 2026, 4:15 p.m.