Triple
T10799167
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William De Witt |
E254792
|
entity |
| Predicate | hasTypicalNationality |
P56478
|
FINISHED |
| Object | 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: American | Statement: [William De Witt, hasTypicalNationality, American]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypicalNationality Context triple: [William De Witt, hasTypicalNationality, American]
-
A.
hasTypicalCitizenship
chosen
Indicates that an entity is generally or commonly a citizen of a specified country or jurisdiction.
-
B.
hasOwnerNationalityStereotype
Indicates that an entity is associated with a stereotype about the nationality of its owner.
-
C.
nationalityOfPersonReferredTo
Indicates that one entity is the country or nationality associated with the person referenced by the other entity.
-
D.
nationalityInText
Indicates that a person's nationality is mentioned or specified within a given text.
-
E.
hasNationalityTraditionally
Indicates that an entity is traditionally or historically associated with a particular nationality, regardless of current legal or formal citizenship status.
- 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_69d6aa61c15c8190a1839550c56e75e1 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d733366c408190bfd3b57be5ef2440 |
completed | April 9, 2026, 5:03 a.m. |
| PD | Predicate disambiguation | batch_69d6f3188f00819094ee8d65b187a333 |
completed | April 9, 2026, 12:30 a.m. |
Created at: April 8, 2026, 9:17 p.m.