Triple
T29467202
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abzakh |
E747411
|
entity |
| Predicate | ethnonymInAdyghe |
P58738
|
FINISHED |
| Object | Абдзахъ (Abdzakh) |
—
|
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: Абдзахъ (Abdzakh) | Statement: [Abzakh, ethnonymInAdyghe, Абдзахъ (Abdzakh)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ethnonymInAdyghe Context triple: [Abzakh, ethnonymInAdyghe, Абдзахъ (Abdzakh)]
-
A.
ethnonym
Indicates that one entity is the name of an ethnic group used to refer to the people associated with another entity.
-
B.
ethnonymInLanguage
chosen
Indicates that a given term is the name used in a specified language to refer to the people of a particular ethnic group or nationality.
-
C.
ethnonymSingular
Indicates that the subject is the singular form of an ethnonym (a name for a member of a specific ethnic or national group).
-
D.
ethnonymAttestedIn
Indicates that the name of an ethnic group (ethnonym) is documented or recorded in a specified source, context, or medium.
-
E.
ethnonymPlural
Indicates the plural form of an ethnonym, expressing how the name of a people or ethnic group is written when referring to multiple members.
- 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_69f0bd42cf308190bb01b20bc5b7c2d0 |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f66ba8898c8190abf0cb6790a11dcd |
completed | May 2, 2026, 9:24 p.m. |
| PD | Predicate disambiguation | batch_69f66339175c819080bd70f0ff7057b1 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 28, 2026, 3:54 p.m.