Triple
T457422
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | European Roma Rights Centre |
E7262
|
entity |
| Predicate | researchTopics |
P934
|
FINISHED |
| Object | segregation in 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: segregation in education | Statement: [European Roma Rights Centre, researchTopics, segregation in education]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: researchTopics Context triple: [European Roma Rights Centre, researchTopics, segregation in education]
-
A.
researchContext
Indicates the situational, methodological, or thematic setting within which a particular piece of research is conducted or interpreted.
-
B.
researchClassification
Indicates that an entity is assigned a specific category or type within a research-related classification scheme.
-
C.
researchProgram
Indicates that an entity is engaged in, associated with, or part of a structured research initiative or program.
-
D.
researchStrength
Indicates the degree to which an entity possesses strong capabilities, performance, or impact in conducting research.
-
E.
hasResearchArea
chosen
Indicates that an entity (such as a person, project, or organization) is associated with or focused on a particular field or area of research.
- 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_69a2e7e5c5bc8190a1dc8178218fba40 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2efa1616481909399f92551a0c9e3 |
completed | Feb. 28, 2026, 1:37 p.m. |
| PD | Predicate disambiguation | batch_69a2ede614b88190be07425f5535f56d |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.