Triple
T22259111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | M27 |
E550170
|
entity |
| Predicate | hasJunction |
P1018
|
FINISHED |
| Object |
Junction 19
Junction 19 is a major interchange on England’s M27 motorway, connecting regional traffic routes along the south coast.
|
E1527333
|
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: Junction 19 | Statement: [M27, hasJunction, Junction 19]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Junction 19 Context triple: [M27, hasJunction, Junction 19]
-
A.
Junction 1
Junction 1 is a key interchange on the M60 motorway near Stockport, connecting local roads to the orbital route around Greater Manchester.
-
B.
Junction 1
Junction 1 is a motorway interchange on the M20 in southeast England, providing access between the M20 and local roads near the London orbital route.
-
C.
Junction 1
Junction 1 is a major road interchange on England’s M58 motorway, connecting it with local and regional routes.
-
D.
Junction 2
Junction 2 is a numbered interchange on the M66 motorway in Greater Manchester, England, providing access between the motorway and local road networks.
-
E.
Junction 2
Junction 2 is a numbered interchange on the M60 motorway in Greater Manchester, England, connecting local roads to the orbital route around Manchester.
- 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: Junction 19 Triple: [M27, hasJunction, Junction 19]
Generated description
Junction 19 is a major interchange on England’s M27 motorway, connecting regional traffic routes along the south coast.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Junction 19 Target entity description: Junction 19 is a major interchange on England’s M27 motorway, connecting regional traffic routes along the south coast.
-
A.
Junction 1
Junction 1 is a motorway interchange on the M20 in southeast England, providing access between the M20 and local roads near the London orbital route.
-
B.
Junction 1
Junction 1 is a key interchange on the M60 motorway near Stockport, connecting local roads to the orbital route around Greater Manchester.
-
C.
Junction 1
Junction 1 is a major road interchange on England’s M58 motorway, connecting it with local and regional routes.
-
D.
Junction 2
Junction 2 is a numbered interchange on the M66 motorway in Greater Manchester, England, providing access between the motorway and local road networks.
-
E.
Junction 2
Junction 2 is a numbered interchange on the M60 motorway in Greater Manchester, England, connecting local roads to the orbital route around Manchester.
- 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_69e11e42adb8819087714772ea606709 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f138c5b54c8190854690ba599639fa |
completed | April 28, 2026, 10:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0ab6681d5881909345d8e83791ba7d |
completed | May 18, 2026, 6:49 a.m. |
| NEDg | Description generation | batch_6a0ab6fd3a6881908ea1e8f85eb9d969 |
completed | May 18, 2026, 6:51 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0ab791bd6c819098b3de570bd08815 |
completed | May 18, 2026, 6:54 a.m. |
Created at: April 16, 2026, 8:39 p.m.