Triple
T3583292
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St David’s Hall |
E75850
|
entity |
| Predicate | locatedOn |
P40
|
FINISHED |
| Object |
The Hayes
The Hayes is a prominent pedestrianised shopping street and public thoroughfare in the centre of Cardiff, Wales.
|
E371802
|
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: The Hayes | Statement: [St David’s Hall, locatedOn, The Hayes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Hayes Context triple: [St David’s Hall, locatedOn, The Hayes]
-
A.
Harding
Harding is the surname of Warren G. Harding, the 29th president of the United States who served from 1921 to 1923.
-
B.
Thomas Hatfield
Thomas Hatfield was a 14th-century Bishop of Durham and influential English cleric and statesman.
-
C.
Sterling Hayes
Sterling Hayes is a Chicago-based rapper and member of the SaveMoney collective known for his introspective lyrics and affiliation with the city's alternative hip-hop scene.
-
D.
John Marsh
John Marsh was the husband of American novelist Margaret Mitchell, best known for supporting her during the creation of "Gone with the Wind."
-
E.
John Lyons
John Lyons is a film producer best known for his work on major Hollywood comedies, including the Austin Powers series.
- 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: The Hayes Triple: [St David’s Hall, locatedOn, The Hayes]
Generated description
The Hayes is a prominent pedestrianised shopping street and public thoroughfare in the centre of Cardiff, Wales.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: The Hayes Target entity description: The Hayes is a prominent pedestrianised shopping street and public thoroughfare in the centre of Cardiff, Wales.
-
A.
Harding
Harding is the surname of Warren G. Harding, the 29th president of the United States who served from 1921 to 1923.
-
B.
Thomas Hatfield
Thomas Hatfield was a 14th-century Bishop of Durham and influential English cleric and statesman.
-
C.
Sterling Hayes
Sterling Hayes is a Chicago-based rapper and member of the SaveMoney collective known for his introspective lyrics and affiliation with the city's alternative hip-hop scene.
-
D.
John Marsh
John Marsh was the husband of American novelist Margaret Mitchell, best known for supporting her during the creation of "Gone with the Wind."
-
E.
John Lyons
John Lyons is a film producer best known for his work on major Hollywood comedies, including the Austin Powers series.
- 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_69ad85d6dc3c8190b491b79b83e25461 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc104846c81908b6fbde7061464b4 |
completed | March 8, 2026, 6:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b402f7ee6481908d06db05f9c09faf |
completed | March 13, 2026, 12:28 p.m. |
| NEDg | Description generation | batch_69b403acc5e88190bc88bed8259393ba |
completed | March 13, 2026, 12:31 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b40a7f82ac819099c2c324ebff76f7 |
completed | March 13, 2026, 1 p.m. |
Created at: March 8, 2026, 3:21 p.m.