Triple
T20481421
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Abdol-Hossein Farmanfarma |
E502461
|
entity |
| Predicate | residence |
P75
|
FINISHED |
| Object | Shiraz |
—
|
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: Shiraz | Statement: [Abdol-Hossein Farmanfarma, residence, Shiraz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shiraz Context triple: [Abdol-Hossein Farmanfarma, residence, Shiraz]
-
A.
Shiraz
Shiraz is a dark-skinned wine grape variety, also known as Syrah, widely used to produce full-bodied red wines around the world.
-
B.
Shiraz, Iran
chosen
Shiraz, Iran is a historic city in southwestern Iran renowned for its rich Persian cultural heritage, poetry, gardens, and wine-making tradition.
-
C.
شیراز
شیراز یکی از مهمترین و تاریخیترین شهرهای ایران است که بهعنوان مرکز فرهنگ، ادب و شعر فارسی شناخته میشود.
-
D.
Shirazi
The Shirazi are a coastal East African ethnic group of mixed African and Persian ancestry, historically influential in the culture and Islamization of regions like Zanzibar.
-
E.
Saveh
Saveh is a historic city in central Iran known as a regional commercial and agricultural center with ancient roots and traditional bazaars.
- 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_69e0b4af32848190aea80682b44d5d6e |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69b56dd248190b6bc4e513aff3c9c |
completed | April 20, 2026, 9:32 p.m. |
Created at: April 16, 2026, 11:34 a.m.