Triple
T21375300
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Banbury Road |
E527185
|
entity |
| Predicate | terminusNorth |
P3375
|
FINISHED |
| Object |
Summertown
Summertown is a prosperous residential and shopping district in north Oxford, England, known for its independent shops, cafes, and proximity to the city’s academic institutions.
|
E1481194
|
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: Summertown | Statement: [Banbury Road, terminusNorth, Summertown]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Summertown Context triple: [Banbury Road, terminusNorth, Summertown]
-
A.
Yorkhill
Yorkhill is a residential neighbourhood in the city of Vaughan, Ontario, known for its diverse community and proximity to Toronto.
-
B.
Milntown
Milntown is a football ground located in Langholm, Scotland, serving as the home venue for the town’s local football activities.
-
C.
Quarry Hill
Quarry Hill is an area in central Leeds, England, known for its cultural institutions and urban redevelopment.
-
D.
Sheffield Bottom
Sheffield Bottom is a small hamlet in Berkshire, England, situated near Burghfield and the Kennet and Avon Canal.
-
E.
Breretonhill
Breretonhill is a locality or hamlet that forms part of the wider Brereton area.
- 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: Summertown Triple: [Banbury Road, terminusNorth, Summertown]
Generated description
Summertown is a prosperous residential and shopping district in north Oxford, England, known for its independent shops, cafes, and proximity to the city’s academic institutions.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Summertown Target entity description: Summertown is a prosperous residential and shopping district in north Oxford, England, known for its independent shops, cafes, and proximity to the city’s academic institutions.
-
A.
Yorkhill
Yorkhill is a residential neighbourhood in the city of Vaughan, Ontario, known for its diverse community and proximity to Toronto.
-
B.
Milntown
Milntown is a football ground located in Langholm, Scotland, serving as the home venue for the town’s local football activities.
-
C.
Quarry Hill
Quarry Hill is an area in central Leeds, England, known for its cultural institutions and urban redevelopment.
-
D.
Sheffield Bottom
Sheffield Bottom is a small hamlet in Berkshire, England, situated near Burghfield and the Kennet and Avon Canal.
-
E.
Breretonhill
Breretonhill is a locality or hamlet that forms part of the wider Brereton area.
- 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_69e0b51e80808190ba5cb05667af02a9 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69ee5bb031988190ae587730a2131a50 |
completed | April 26, 2026, 6:38 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09b420a0288190bb074e6e9a29fdb6 |
completed | May 17, 2026, 12:27 p.m. |
| NEDg | Description generation | batch_6a09b4f828b88190a2b203eef44880f5 |
completed | May 17, 2026, 12:30 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a09b5aeb89c81909569ae7d5b611357 |
completed | May 17, 2026, 12:33 p.m. |
Created at: April 16, 2026, 5:11 p.m.