Triple
T17168535
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tsez language |
E416667
|
entity |
| Predicate | hasNounClassType |
P5217
|
FINISHED |
| Object | gender-like system |
—
|
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: gender-like system | Statement: [Tsez language, hasNounClassType, gender-like system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNounClassType Context triple: [Tsez language, hasNounClassType, gender-like system]
-
A.
hasNounClassCount
Indicates the number of distinct noun classes that are associated with or defined for a given entity.
-
B.
hasNounClassSystem
chosen
Indicates that an entity possesses a grammatical system in which nouns are categorized into distinct classes that affect their agreement with other elements in the language.
-
C.
hasNounDeclensionType
Indicates that a noun is associated with a specific grammatical declension pattern or type.
-
D.
hasNoun
Indicates that an entity possesses or is associated with a specific noun as an attribute, label, or grammatical component.
-
E.
hasNounSystemFrom
Indicates that something possesses or is associated with a noun-based system that originates from or is derived from a specified source.
- 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_69d886d5f34c8190b24564dfaa63f3fb |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3f9173ee48190bc46622c78479603 |
completed | April 18, 2026, 9:35 p.m. |
| PD | Predicate disambiguation | batch_69e3830d2a90819092386717dc56f0e8 |
completed | April 18, 2026, 1:11 p.m. |
Created at: April 10, 2026, 5:37 a.m.