Triple
T36802493
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roma in Hungary |
E909357
|
entity |
| Predicate | discriminatedAgainstIn |
P2109
|
FINISHED |
| Object | education |
—
|
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: education | Statement: [Roma in Hungary, discriminatedAgainstIn, education]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: discriminatedAgainstIn Context triple: [Roma in Hungary, discriminatedAgainstIn, education]
-
A.
discriminatedAgainst
chosen
Indicates that one entity treats another unfairly or unequally based on a particular characteristic, such as race, gender, or other protected attributes.
-
B.
addressesDiscriminationAgainst
Indicates that an action, policy, or measure is specifically aimed at confronting, reducing, or eliminating discrimination directed toward certain individuals or groups.
-
C.
discriminationStatus
Indicates whether an entity is subject to, engaged in, or affected by discriminatory treatment based on protected or distinguishing characteristics.
-
D.
discriminationEmbedded
Indicates that discriminatory attitudes, biases, or practices are ingrained within a system, structure, or process rather than occurring only as isolated or explicit acts.
-
E.
discriminationGround
Indicates the basis or reason (such as a characteristic or attribute) on which discriminatory treatment is applied in the relationship.
- 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_69f76e7b98888190899b6478a82ad6ae |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69f7ca93bd0481909d6eee9e950001a1 |
completed | May 3, 2026, 10:22 p.m. |
| PD | Predicate disambiguation | batch_69f7c89b528c8190bf80b230fc7c7108 |
completed | May 3, 2026, 10:13 p.m. |
Created at: May 3, 2026, 4:12 p.m.