Triple
T1644471
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | River Taff |
E35547
|
entity |
| Predicate | hasBridge |
P386
|
FINISHED |
| Object |
Llandaff Bridge
Llandaff Bridge is a historic road bridge in Cardiff, Wales, carrying traffic across the River Taff near the district of Llandaff.
|
E273083
|
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: Llandaff Bridge | Statement: [River Taff, hasBridge, Llandaff Bridge]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Llandaff Bridge Context triple: [River Taff, hasBridge, Llandaff Bridge]
-
A.
Cardiff Bridge
Cardiff Bridge is a historic road bridge in Cardiff, Wales, carrying traffic across the River Taff near the city centre.
-
B.
Ha'penny Bridge
Ha'penny Bridge is a historic cast-iron pedestrian bridge over the River Liffey and one of Dublin’s most iconic symbols.
-
C.
Queen’s Bridge
Queen’s Bridge is a historic road bridge in Belfast, Northern Ireland, carrying traffic across the River Lagan near the city centre.
-
D.
Queen’s Bridge
Queen’s Bridge is a notable road bridge spanning the River Tay in Perth, Scotland, serving as a key crossing point into the city.
-
E.
Trinity Bridge
Trinity Bridge is a historic steel bascule bridge in Saint Petersburg, Russia, known for its ornate design and role as a major crossing over the Neva River near the city’s central landmarks.
- 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: Llandaff Bridge Triple: [River Taff, hasBridge, Llandaff Bridge]
Generated description
Llandaff Bridge is a historic road bridge in Cardiff, Wales, carrying traffic across the River Taff near the district of Llandaff.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Llandaff Bridge Target entity description: Llandaff Bridge is a historic road bridge in Cardiff, Wales, carrying traffic across the River Taff near the district of Llandaff.
-
A.
Cardiff Bridge
Cardiff Bridge is a historic road bridge in Cardiff, Wales, carrying traffic across the River Taff near the city centre.
-
B.
Ha'penny Bridge
Ha'penny Bridge is a historic cast-iron pedestrian bridge over the River Liffey and one of Dublin’s most iconic symbols.
-
C.
Queen’s Bridge
Queen’s Bridge is a historic road bridge in Belfast, Northern Ireland, carrying traffic across the River Lagan near the city centre.
-
D.
Queen’s Bridge
Queen’s Bridge is a notable road bridge spanning the River Tay in Perth, Scotland, serving as a key crossing point into the city.
-
E.
Trinity Bridge
Trinity Bridge is a historic steel bascule bridge in Saint Petersburg, Russia, known for its ornate design and role as a major crossing over the Neva River near the city’s central landmarks.
- 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_69a88604618c81908b41f6429c431eb6 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aa622e9b08819094960b2329c6e7e6 |
completed | March 6, 2026, 5:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af1f6a15f081909b83d24a7b470eba |
completed | March 9, 2026, 7:28 p.m. |
| NEDg | Description generation | batch_69af20bcdc448190987350d28a525153 |
completed | March 9, 2026, 7:34 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69af2131ed6c81908dcce0d0d4e14bec |
completed | March 9, 2026, 7:36 p.m. |
Created at: March 4, 2026, 7:28 p.m.