Triple
T26073674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Belles |
E657619
|
entity |
| Predicate | associatedDemographic |
P7875
|
FINISHED |
| Object | African American women |
—
|
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: African American women | Statement: [Belles, associatedDemographic, African American women]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedDemographic Context triple: [Belles, associatedDemographic, African American women]
-
A.
hasDemographic
chosen
Indicates that an entity is associated with or characterized by a particular demographic group or attribute.
-
B.
involvesDemographic
Indicates that an action, event, or entity is related to, affects, or includes a specific demographic group or population segment.
-
C.
demographicsDescriptor
Indicates a descriptive attribute or classification that characterizes the demographic properties of an entity or group.
-
D.
demographicCharacteristic
Indicates that one entity specifies or describes a demographic attribute or feature (such as age, gender, ethnicity, or similar population-related trait) of another entity.
-
E.
demographicsCharacteristic
Indicates that one entity serves as a demographic attribute or characteristic (such as age, gender, ethnicity, etc.) that describes or classifies another entity.
- 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_69ee5bbe539081909efc7f9dd7c1b53c |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69fe9b0276d48190b554fa22b043e6d8 |
completed | May 9, 2026, 2:25 a.m. |
| PD | Predicate disambiguation | batch_69fe999692b081909921e1148d66f0ef |
completed | May 9, 2026, 2:19 a.m. |
Created at: April 26, 2026, 7:31 p.m.