Triple
T78471
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Black Americans |
E1571
|
entity |
| Predicate | face |
P3326
|
FINISHED |
| Object | racial discrimination |
—
|
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: racial discrimination | Statement: [Black Americans, face, racial discrimination]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: face Context triple: [Black Americans, face, racial discrimination]
-
A.
facesChallenge
chosen
Indicates that an entity is confronted with a difficulty, obstacle, or demanding situation that must be dealt with or overcome.
-
B.
front
Indicates that one entity is located directly before or facing another entity along a primary viewing or movement direction.
-
C.
eagleFaces
Indicates that an eagle is oriented toward, looking at, or facing another entity or direction.
-
D.
frontType
Indicates the type or category of a front (e.g., boundary or leading side) that one entity presents or forms relative to another.
-
E.
mouth
Indicates that one entity is the mouth (oral opening) of another entity, typically serving as the location for ingestion, speech, or related functions.
- 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_69a24c60d19c8190a1b6c105ca59ef5b |
completed | Feb. 28, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69a2559892dc81909303f2eefdc0025f |
completed | Feb. 28, 2026, 2:40 a.m. |
| PD | Predicate disambiguation | batch_69a24eaf99e481908e8d314577e22ecf |
completed | Feb. 28, 2026, 2:10 a.m. |
Created at: Feb. 28, 2026, 2:06 a.m.