Triple
T11868764
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Purnia district |
E282352
|
entity |
| Predicate | hasCity |
P316
|
FINISHED |
| Object |
Banmankhi
Banmankhi is a town and administrative block in the Purnia district of Bihar, India, known primarily as a local commercial and agricultural center.
|
E951034
|
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: Banmankhi | Statement: [Purnia district, hasCity, Banmankhi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Banmankhi Context triple: [Purnia district, hasCity, Banmankhi]
-
A.
Mangdechhu
Mangdechhu is a river in Bhutan known for flowing through ecologically rich protected areas and hosting major hydropower projects.
-
B.
Thantlang
Thantlang is a town in western Myanmar known for its predominantly Chin population and its location in the hilly, remote region near the India–Myanmar border.
-
C.
Mongnai
Mongnai is a historic town and former princely state in Myanmar’s Shan region, known for its role within the traditional Shan States.
-
D.
Bomdila
Bomdila is a hill town in northeastern India known for its Buddhist monasteries, scenic Himalayan views, and role as a cultural and administrative center in the region.
-
E.
Tonsawang
Tonsawang is an Austronesian language spoken by the Tonsawang people in North Sulawesi, Indonesia.
- 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: Banmankhi Triple: [Purnia district, hasCity, Banmankhi]
Generated description
Banmankhi is a town and administrative block in the Purnia district of Bihar, India, known primarily as a local commercial and agricultural center.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Banmankhi Target entity description: Banmankhi is a town and administrative block in the Purnia district of Bihar, India, known primarily as a local commercial and agricultural center.
-
A.
Mangdechhu
Mangdechhu is a river in Bhutan known for flowing through ecologically rich protected areas and hosting major hydropower projects.
-
B.
Thantlang
Thantlang is a town in western Myanmar known for its predominantly Chin population and its location in the hilly, remote region near the India–Myanmar border.
-
C.
Mongnai
Mongnai is a historic town and former princely state in Myanmar’s Shan region, known for its role within the traditional Shan States.
-
D.
Bomdila
Bomdila is a hill town in northeastern India known for its Buddhist monasteries, scenic Himalayan views, and role as a cultural and administrative center in the region.
-
E.
Tonsawang
Tonsawang is an Austronesian language spoken by the Tonsawang people in North Sulawesi, Indonesia.
- 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_69d6ab2945d081908a5851c916cbcfb5 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a73c04e4819084c0b2ff8e5d2f04 |
completed | April 10, 2026, 7:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f281a2abfc8190a4769e637dedaaab |
completed | April 29, 2026, 10:09 p.m. |
| NEDg | Description generation | batch_69f28a92ac90819092eef473a49d329e |
completed | April 29, 2026, 10:47 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f28c462d888190a43e042b00921dbe |
completed | April 29, 2026, 10:55 p.m. |
Created at: April 8, 2026, 9:43 p.m.