Triple
T15040393
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Söderort |
E378584
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object |
Bandhagen
Bandhagen is a residential district in southern Stockholm, Sweden, known for its post-war housing and proximity to the city’s metro network.
|
E1132932
|
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: Bandhagen | Statement: [Söderort, hasPart, Bandhagen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bandhagen Context triple: [Söderort, hasPart, Bandhagen]
-
A.
Bandhej
Bandhej is a traditional Indian tie-dye textile art form known for its intricate patterns created by resist-dyeing tightly knotted fabric, especially popular in regions like Gujarat and Rajasthan.
-
B.
Kordon
Kordon is a famous seafront promenade and social hub in İzmir, Turkey, known for its scenic views, cafes, and lively atmosphere along the Aegean coast.
-
C.
Bandhi
Bandhi is a small town located in the Nawabshah (Shaheed Benazirabad) District of Sindh province in Pakistan.
-
D.
Bann
Bann is an alternative name for the River Bann, one of the longest and most significant rivers in Northern Ireland.
-
E.
Kabandha
Kabandha is a fearsome, deformed rakshasa (demon) from the Indian epic Ramayana, known for his monstrous trunk-like body and encounter with Rama and Lakshmana in the forest.
- 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: Bandhagen Triple: [Söderort, hasPart, Bandhagen]
Generated description
Bandhagen is a residential district in southern Stockholm, Sweden, known for its post-war housing and proximity to the city’s metro network.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bandhagen Target entity description: Bandhagen is a residential district in southern Stockholm, Sweden, known for its post-war housing and proximity to the city’s metro network.
-
A.
Bandhej
Bandhej is a traditional Indian tie-dye textile art form known for its intricate patterns created by resist-dyeing tightly knotted fabric, especially popular in regions like Gujarat and Rajasthan.
-
B.
Kordon
Kordon is a famous seafront promenade and social hub in İzmir, Turkey, known for its scenic views, cafes, and lively atmosphere along the Aegean coast.
-
C.
Bandhi
Bandhi is a small town located in the Nawabshah (Shaheed Benazirabad) District of Sindh province in Pakistan.
-
D.
Bann
Bann is an alternative name for the River Bann, one of the longest and most significant rivers in Northern Ireland.
-
E.
Kabandha
Kabandha is a fearsome, deformed rakshasa (demon) from the Indian epic Ramayana, known for his monstrous trunk-like body and encounter with Rama and Lakshmana in the forest.
- 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_69d85cd46b2c819090d054c27787f677 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded82e79a481908ddb9609af8c4407 |
completed | April 15, 2026, 12:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe9de388508190bb0ecc04740cbe15 |
completed | May 9, 2026, 2:37 a.m. |
| NEDg | Description generation | batch_69fe9f2b71808190b961193ae1ddebf0 |
completed | May 9, 2026, 2:42 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69fe9fa89bd481909235d2ec377a0d8e |
completed | May 9, 2026, 2:44 a.m. |
Created at: April 10, 2026, 3 a.m.