Triple
T26974444
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fred Sanford |
E679410
|
entity |
| Predicate | raceEthnicity |
P130133
|
FINISHED |
| Object | African-American |
—
|
NE NERFINISHED |
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: African-American | Statement: [Fred Sanford, raceEthnicity, African-American]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: raceEthnicity Context triple: [Fred Sanford, raceEthnicity, African-American]
-
A.
raceRole
Indicates the specific role, position, or function an entity holds within a race or racing event.
-
B.
raceGroup
chosen
Indicates that the subject belongs to, or is categorized within, a particular racial or ethnic group.
-
C.
racialComposition
Indicates the proportional makeup of different racial groups within a given population or entity.
-
D.
holderEthnicity
Indicates the ethnic background or group to which the holder of something (e.g., a document, account, or item) belongs.
-
E.
racialIdentity
Indicates the relationship between an entity and the racial group or classification with which it is identified or categorized.
- 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_69eeeb507a7081909d516e1fa08b7d29 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f621273ac4819083f71dbebe55b082 |
completed | May 2, 2026, 4:07 p.m. |
| PD | Predicate disambiguation | batch_69f611af72ac819094598dd2530d7411 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 6:41 a.m.