Triple
T1644462
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | River Taff |
E35547
|
entity |
| Predicate | flowsThrough |
P225
|
FINISHED |
| Object |
Llandaff
Llandaff is a historic district of Cardiff in Wales, best known for its medieval cathedral and long-standing ecclesiastical significance.
|
E227491
|
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 | Statement: [River Taff, flowsThrough, Llandaff]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Llandaff Context triple: [River Taff, flowsThrough, Llandaff]
-
A.
Llantrisant
Llantrisant is a historic Welsh town known for its medieval heritage and hilltop setting in South Wales.
-
B.
Bridgend
Bridgend is a small village on the Scottish island of Islay, known for its rural setting and role as a local hub near the island’s central crossroads.
-
C.
Bridgend
Bridgend is a town and county borough in South Wales, situated roughly midway between Cardiff and Swansea and known historically for its market and industrial heritage.
-
D.
Cowbridge
Cowbridge is a historic market town in South Wales known for its medieval origins, independent shops, and well-preserved high street.
-
E.
Ystrad Mynach
Ystrad Mynach is a town in south Wales known as a local administrative and commercial centre within the Caerphilly 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: Llandaff Triple: [River Taff, flowsThrough, Llandaff]
Generated description
Llandaff is a historic district of Cardiff in Wales, best known for its medieval cathedral and long-standing ecclesiastical significance.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Llandaff Target entity description: Llandaff is a historic district of Cardiff in Wales, best known for its medieval cathedral and long-standing ecclesiastical significance.
-
A.
Llantrisant
Llantrisant is a historic Welsh town known for its medieval heritage and hilltop setting in South Wales.
-
B.
Bridgend
Bridgend is a small village on the Scottish island of Islay, known for its rural setting and role as a local hub near the island’s central crossroads.
-
C.
Bridgend
Bridgend is a town and county borough in South Wales, situated roughly midway between Cardiff and Swansea and known historically for its market and industrial heritage.
-
D.
Cowbridge
Cowbridge is a historic market town in South Wales known for its medieval origins, independent shops, and well-preserved high street.
-
E.
Ystrad Mynach
Ystrad Mynach is a town in south Wales known as a local administrative and commercial centre within the Caerphilly 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_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_69ae1fb8b14c8190abbcc24f17fa8243 |
completed | March 9, 2026, 1:17 a.m. |
| NEDg | Description generation | batch_69ae204fe6148190915219beb27128bc |
completed | March 9, 2026, 1:20 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ae20d09c748190aebbfb88f0eedbaa |
completed | March 9, 2026, 1:22 a.m. |
Created at: March 4, 2026, 7:28 p.m.