Triple
T15801271
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zaydi kalam |
E383102
|
entity |
| Predicate | developedInRegion |
P9365
|
FINISHED |
| Object | Daylam |
E1077994
|
NE 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: Daylam | Statement: [Zaydi kalam, developedInRegion, Daylam]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Daylam Context triple: [Zaydi kalam, developedInRegion, Daylam]
-
A.
Daylam
chosen
Daylam was a mountainous historical region in northern Iran, inhabited by the Daylamite people and known for its fierce warriors and relative autonomy from surrounding empires.
-
B.
Marivan
Marivan is a Kurdish-populated city in western Iran near the Iraqi border, known for its scenic Zarivar Lake and role as a regional commercial and cultural center.
-
C.
Hawezar
Hawezar is a swampy, treacherous region in the Diablo universe’s world of Sanctuary, known for its deadly marshes, dark magic, and ruthless inhabitants.
-
D.
Azarbarzin
Azarbarzin is a character from Persian epic tradition, known primarily as the son of the legendary hero Esfandiyar.
-
E.
Jahan
Jahan is a Persian-derived term meaning "world" or "universe," commonly used in royal and honorific titles across South and Central Asia.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d86da16e188190b89af699f1ed0bfe |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e0b522a2988190b2a2bde2da31b21e |
completed | April 16, 2026, 10:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff998b52e481908baa20b5a8c1cbcf |
completed | May 9, 2026, 8:31 p.m. |
Created at: April 10, 2026, 4:48 a.m.