Triple
T37688674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Treaty of Purandar (1665) |
E938441
|
entity |
| Predicate | languageLikelyUsed |
P140303
|
FINISHED |
| Object | Persian |
—
|
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: Persian | Statement: [Treaty of Purandar (1665), languageLikelyUsed, Persian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageLikelyUsed Context triple: [Treaty of Purandar (1665), languageLikelyUsed, Persian]
-
A.
probableLanguageType
chosen
Indicates that something is likely to belong to, be expressed in, or be categorized under a particular language or type of language.
-
B.
languageUsedAs
Indicates that one language is employed in a specific role, function, or context relative to another entity or situation.
-
C.
languageGroupSpoken
Indicates that a particular language group is spoken or used for communication by an entity.
-
D.
mainLanguageOf
Indicates that a specified language is the primary or dominant language used by a particular entity (such as a person, document, or organization).
-
E.
languageBranchOfDialectSpoken
Indicates that one language branch is the higher-level linguistic group from which a given spoken dialect originates or to which that dialect belongs.
- 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_69f76ed881408190bc62a969530a4a53 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a01a534a8908190aa888d6be5deb824 |
completed | May 11, 2026, 9:45 a.m. |
| PD | Predicate disambiguation | batch_6a01a507c1f081909ff6abc5575db0bb |
completed | May 11, 2026, 9:44 a.m. |
Created at: May 3, 2026, 4:18 p.m.