Triple
T17921996
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Manjil |
E448094
|
entity |
| Predicate | languageSpoken |
P151
|
FINISHED |
| Object | Gilaki |
—
|
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: Gilaki | Statement: [Manjil, languageSpoken, Gilaki]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gilaki Context triple: [Manjil, languageSpoken, Gilaki]
-
A.
Gilaki
chosen
Gilaki is an Iranian language spoken primarily in Iran’s Gilan Province along the Caspian Sea coast.
-
B.
Bakhtiari Luri
Bakhtiari Luri is a major Southwestern Iranian dialect spoken primarily by the Bakhtiari people of western and southwestern Iran.
-
C.
Mazanderani language
Mazanderani language is a Northwestern Iranian language spoken primarily along Iran’s southern Caspian Sea coast, especially in Mazandaran Province.
-
D.
Northern Luri
Northern Luri is a major variety of the Luri language spoken by Lur communities in western Iran, distinguished by its own phonological and lexical features.
-
E.
Central Luri
Central Luri is a major variety of the Luri language spoken by Lur communities in western Iran, characterized by features transitional between Persian and Kurdish.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9f6d394819082a6d69fd1e23d2f |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4a30ad8748190b28d3e8b5afab2ef |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, 10:20 a.m.