Triple
T1020731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | American |
E22033
|
entity |
| Predicate | canHaveNativeLanguage |
P151
|
FINISHED |
| Object | any language |
—
|
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: any language | Statement: [American, canHaveNativeLanguage, any language]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canHaveNativeLanguage Context triple: [American, canHaveNativeLanguage, any language]
-
A.
hasNativeSpeakers
Indicates that a language or dialect is spoken as a first language by one or more people or populations.
-
B.
hasLanguageOn
Indicates that an entity uses or is associated with a particular language in a specific context, medium, or location.
-
C.
hasSecondaryLanguage
Indicates that an entity possesses or uses a secondary language in addition to its primary language.
-
D.
hasMemberLanguage
Indicates that one entity is a language that is a constituent or member of a larger language group, family, or collection represented by the other entity.
-
E.
nativeLanguage
chosen
Indicates the language that a person or entity originally learned and uses as their primary or first language.
- 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_69a493d6e380819097b384986ffc315c |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b7dd76b081909ed4d2f7adb6480d |
completed | March 1, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69a4b724c7908190a5b92a57fbdbff4e |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:41 p.m.