Triple
T409661
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | London Euston |
E9460
|
entity |
| Predicate | connectedTo |
P37
|
FINISHED |
| Object |
Midland Road
Midland Road is a street in central London near major rail terminals such as St Pancras and King’s Cross, forming part of a key transport hub area.
|
E117290
|
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: Midland Road | Statement: [London Euston, connectedTo, Midland Road]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Midland Road Context triple: [London Euston, connectedTo, Midland Road]
-
A.
Weston Road
Weston Road is a major north–south arterial route in the Greater Toronto Area that runs through communities such as Woodbridge in Vaughan.
-
B.
Oxford Road
Oxford Road is a major thoroughfare in Manchester, England, known for its concentration of university buildings, cultural institutions, and transport links.
-
C.
Moor Road
Moor Road is a tram stop on Greater Manchester’s Metrolink light rail network in the UK.
-
D.
Columbia Road
Columbia Road is a former name of the JFK/UMass transit station in Boston, Massachusetts.
-
E.
Newell Highway
Newell Highway is a major inland highway in New South Wales, Australia, forming a key north–south freight and transport route through regions including the Riverina.
- 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: Midland Road Triple: [London Euston, connectedTo, Midland Road]
Generated description
Midland Road is a street in central London near major rail terminals such as St Pancras and King’s Cross, forming part of a key transport hub area.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Midland Road Target entity description: Midland Road is a street in central London near major rail terminals such as St Pancras and King’s Cross, forming part of a key transport hub area.
-
A.
Weston Road
Weston Road is a major north–south arterial route in the Greater Toronto Area that runs through communities such as Woodbridge in Vaughan.
-
B.
Oxford Road
Oxford Road is a major thoroughfare in Manchester, England, known for its concentration of university buildings, cultural institutions, and transport links.
-
C.
Moor Road
Moor Road is a tram stop on Greater Manchester’s Metrolink light rail network in the UK.
-
D.
Columbia Road
Columbia Road is a former name of the JFK/UMass transit station in Boston, Massachusetts.
-
E.
Newell Highway
Newell Highway is a major inland highway in New South Wales, Australia, forming a key north–south freight and transport route through regions including the Riverina.
- 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_69a2e80111fc8190961d5b7c6154123f |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2ecc098c4819088d127c5ea55ced9 |
completed | Feb. 28, 2026, 1:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac256a80f08190841759d0f6132e24 |
completed | March 7, 2026, 1:17 p.m. |
| NEDg | Description generation | batch_69ac2641aee88190985d644563c8f602 |
completed | March 7, 2026, 1:21 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ac26e269b081908398530ad3fa23bc |
completed | March 7, 2026, 1:23 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.