Triple
T9925435
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arak |
E187909
|
entity |
| Predicate | formerName |
P65
|
FINISHED |
| Object |
Sultanabad
Sultanabad is the former name of the Iranian city now known as Arak, an important industrial and historical center in central Iran.
|
E829871
|
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: Sultanabad | Statement: [Arak, formerName, Sultanabad]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sultanabad Context triple: [Arak, formerName, Sultanabad]
-
A.
Mahmudabad
Mahmudabad is a coastal city in northern Iran, situated along the Caspian Sea in Mazandaran Province and known for its beaches and tourism.
-
B.
Nasirabad
Nasirabad is a town and administrative area located in the Balochistan region of present-day Pakistan.
-
C.
Shamshabad
Shamshabad is a suburban area near Hyderabad in the Indian state of Telangana, known primarily for hosting the Rajiv Gandhi International Airport.
-
D.
Mehmedabad
Mehmedabad is a town in the Kheda district of Gujarat, India, known for its historical significance and location along key regional transport routes.
-
E.
Asadabad
Asadabad is a small but strategically important city in eastern Afghanistan, serving as the capital of Kunar Province near the Pakistani border.
- 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: Sultanabad Triple: [Arak, formerName, Sultanabad]
Generated description
Sultanabad is the former name of the Iranian city now known as Arak, an important industrial and historical center in central Iran.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sultanabad Target entity description: Sultanabad is the former name of the Iranian city now known as Arak, an important industrial and historical center in central Iran.
-
A.
Mahmudabad
Mahmudabad is a coastal city in northern Iran, situated along the Caspian Sea in Mazandaran Province and known for its beaches and tourism.
-
B.
Shamshabad
Shamshabad is a suburban area near Hyderabad in the Indian state of Telangana, known primarily for hosting the Rajiv Gandhi International Airport.
-
C.
Nasirabad
Nasirabad is a town and administrative area located in the Balochistan region of present-day Pakistan.
-
D.
Mehmedabad
Mehmedabad is a town in the Kheda district of Gujarat, India, known for its historical significance and location along key regional transport routes.
-
E.
Asadabad
Asadabad is a small but strategically important city in eastern Afghanistan, serving as the capital of Kunar Province near the Pakistani border.
- 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_69ca82b22a688190b52c75bd48429c10 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cdb599e32c8190ac676fa89c131bb6 |
completed | April 2, 2026, 12:17 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d20e143660819097a9fa96365bc25a |
completed | April 5, 2026, 7:24 a.m. |
| NEDg | Description generation | batch_69d21318b3008190af5db2bfb53bc2c6 |
completed | April 5, 2026, 7:45 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d213b979e88190ad5a4f72784a0fe6 |
completed | April 5, 2026, 7:48 a.m. |
Created at: March 30, 2026, 8:43 p.m.