Triple
T5005547
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Worcester, England |
E112481
|
entity |
| Predicate | hasLandmark |
P105
|
FINISHED |
| Object |
Worcester Bridge
Worcester Bridge is a historic road bridge spanning the River Severn in Worcester, England, serving as a key crossing point into the city.
|
E527387
|
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: Worcester Bridge | Statement: [Worcester, England, hasLandmark, Worcester Bridge]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Worcester Bridge Context triple: [Worcester, England, hasLandmark, Worcester Bridge]
-
A.
Radcliffe Bridge
Radcliffe Bridge is a notable local bridge and landmark in the town of Radcliffe, England.
-
B.
Cromwell Bridge
Cromwell Bridge is a historic stone bridge in Lancashire, England, known for carrying traffic across the River Hodder near the village of Hurst Green.
-
C.
Abingdon Bridge
Abingdon Bridge is a historic stone road bridge over the River Thames in Abingdon, Oxfordshire, England.
-
D.
Runnymede Bridge
Runnymede Bridge is a road bridge over the River Thames in Surrey, England, carrying the M25 motorway near the historic meadow of Runnymede.
-
E.
Sandfield Bridge
Sandfield Bridge is a road bridge spanning the Gloucester and Sharpness Canal in Gloucestershire, England.
- 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: Worcester Bridge Triple: [Worcester, England, hasLandmark, Worcester Bridge]
Generated description
Worcester Bridge is a historic road bridge spanning the River Severn in Worcester, England, serving as a key crossing point into the city.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Worcester Bridge Target entity description: Worcester Bridge is a historic road bridge spanning the River Severn in Worcester, England, serving as a key crossing point into the city.
-
A.
Radcliffe Bridge
Radcliffe Bridge is a notable local bridge and landmark in the town of Radcliffe, England.
-
B.
Cromwell Bridge
Cromwell Bridge is a historic stone bridge in Lancashire, England, known for carrying traffic across the River Hodder near the village of Hurst Green.
-
C.
Abingdon Bridge
Abingdon Bridge is a historic stone road bridge over the River Thames in Abingdon, Oxfordshire, England.
-
D.
Runnymede Bridge
Runnymede Bridge is a road bridge over the River Thames in Surrey, England, carrying the M25 motorway near the historic meadow of Runnymede.
-
E.
Sandfield Bridge
Sandfield Bridge is a road bridge spanning the Gloucester and Sharpness Canal in Gloucestershire, England.
- 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_69bd4433d0b08190877e83959ef40d81 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd72e63a0c8190abf697c2e3dc2bf0 |
completed | March 20, 2026, 4:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bfe61a2cd8819089ea67309d284be4 |
completed | March 22, 2026, 12:52 p.m. |
| NEDg | Description generation | batch_69bfe686b99881908bb9a952d5c120c9 |
completed | March 22, 2026, 12:54 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69bfe6e8d18c8190a676e59cd16d6b12 |
completed | March 22, 2026, 12:56 p.m. |
Created at: March 20, 2026, 1:35 p.m.