Triple
T10153469
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sanandaj |
E232707
|
entity |
| Predicate | roadConnectionTo |
P9041
|
FINISHED |
| Object | Marivan |
E800457
|
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: Marivan | Statement: [Sanandaj, roadConnectionTo, Marivan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marivan Context triple: [Sanandaj, roadConnectionTo, Marivan]
-
A.
Marivan
chosen
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.
-
B.
Margilan
Margilan is a historic city in eastern Uzbekistan renowned as a traditional center of silk production and trade along the Silk Road.
-
C.
Ardabil
Ardabil is a historic city in northwestern Iran known for its cultural heritage, including the UNESCO-listed Sheikh Safi al-Din Khānegāh and Shrine Ensemble.
-
D.
Damghan
Damghan is an ancient city in north-central Iran known for its historical monuments and archaeological sites, including one of the oldest mosques in the country.
-
E.
Mozzafarieh
Mozzafarieh is a notable section of the Tabriz Historic Bazaar Complex, traditionally associated with specialized trade and craftsmanship within the bazaar.
- 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_69ca84885e48819088a31b127cf44904 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cdec376cd48190990862c56c3a4dce |
completed | April 2, 2026, 4:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d98811fd3881909369e0f00f2a8267 |
completed | April 10, 2026, 11:30 p.m. |
Created at: March 30, 2026, 9:08 p.m.