Triple
T7171882
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Princess Lilibet of Sussex |
E167218
|
entity |
| Predicate | maternalEthnicity |
P50958
|
FINISHED |
| Object | African American |
—
|
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 | Statement: [Princess Lilibet of Sussex, maternalEthnicity, African American]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maternalEthnicity Context triple: [Princess Lilibet of Sussex, maternalEthnicity, African American]
-
A.
spouseEthnicity
Indicates the ethnic background or identity of a person’s spouse.
-
B.
ethnicOrigin
Indicates the relationship where an entity is associated with a particular ethnic group or ancestry.
-
C.
laterEthnicIdentity
Indicates that an entity’s ethnic identity is associated with or applies to a later period in time relative to some earlier state or context.
-
D.
hasMotherOrigin
chosen
Indicates that an entity’s origin, source, or lineage is derived from or attributed to a mother entity.
-
E.
maternalHouse
Indicates the house or family line associated with an entity’s mother, typically representing maternal ancestry or origin.
- 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_69c68889a2748190a316c5e65360361a |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e88b0a448190a19bd2d9e2a310a4 |
completed | March 27, 2026, 8:28 p.m. |
| PD | Predicate disambiguation | batch_69c6e1ce5f048190808c378a980f7bb6 |
completed | March 27, 2026, 8 p.m. |
Created at: March 27, 2026, 2:48 p.m.