Triple
T2038950
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iranian Azerbaijan |
E44697
|
entity |
| Predicate | hasMajorCity |
P316
|
FINISHED |
| Object |
Sarab
Sarab is a city in northwestern Iran known for its location in East Azerbaijan Province and its surrounding volcanic mineral springs.
|
E229945
|
NE FINISHED |
How this triple was built (4 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: Sarab | Statement: [Iranian Azerbaijan, hasMajorCity, Sarab]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sarab Context triple: [Iranian Azerbaijan, hasMajorCity, Sarab]
-
A.
Sadras
Sadras is a historic coastal town in Tamil Nadu, India, known for its Dutch-era fort and role as a former trading port on the Coromandel Coast.
-
B.
Nasirabad
Nasirabad is a town and administrative area located in the Balochistan region of present-day Pakistan.
-
C.
Bandar Shahpur
Bandar Shahpur is a port city in southwestern Iran on the Persian Gulf that historically served as a key maritime and logistical hub, including during World War II supply routes.
-
D.
Darband
Darband is another name for Derbent, an ancient fortified city on the Caspian Sea in present-day Dagestan, Russia, known for its strategic mountain pass and historic defensive walls.
-
E.
Gorgan
Gorgan is a city in northern Iran, serving as the capital of Golestan Province near the southeastern coast of the Caspian Sea.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Sarab Triple: [Iranian Azerbaijan, hasMajorCity, Sarab]
Generated description
Sarab is a city in northwestern Iran known for its location in East Azerbaijan Province and its surrounding volcanic mineral springs.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sarab Target entity description: Sarab is a city in northwestern Iran known for its location in East Azerbaijan Province and its surrounding volcanic mineral springs.
-
A.
Sadras
Sadras is a historic coastal town in Tamil Nadu, India, known for its Dutch-era fort and role as a former trading port on the Coromandel Coast.
-
B.
Nasirabad
Nasirabad is a town and administrative area located in the Balochistan region of present-day Pakistan.
-
C.
Bandar Shahpur
Bandar Shahpur is a port city in southwestern Iran on the Persian Gulf that historically served as a key maritime and logistical hub, including during World War II supply routes.
-
D.
Darband
Darband is another name for Derbent, an ancient fortified city on the Caspian Sea in present-day Dagestan, Russia, known for its strategic mountain pass and historic defensive walls.
-
E.
Gorgan
Gorgan is a city in northern Iran, serving as the capital of Golestan Province near the southeastern coast of the Caspian Sea.
- F. None of above. chosen
Provenance (5 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_69a889159ec481908f9e4472d9f480c7 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb951870481909dbdd8fc8b0c02fe |
completed | March 7, 2026, 5:36 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae1ff63de081908795a95c998dd9ac |
completed | March 9, 2026, 1:18 a.m. |
| NEDg | Description generation | batch_69ae20a6ce14819098007416d6377f2e |
completed | March 9, 2026, 1:21 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ae2130ba448190b91f590a348ebf88 |
completed | March 9, 2026, 1:24 a.m. |
Created at: March 4, 2026, 7:39 p.m.