Triple
T753745
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crumlin Road Gaol |
E15506
|
entity |
| Predicate | architect |
P184
|
FINISHED |
| Object |
Charles Lanyon
Charles Lanyon was a prominent 19th-century Irish architect known for designing many notable public buildings in Belfast and across Ulster.
|
E95861
|
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: Charles Lanyon | Statement: [Crumlin Road Gaol, architect, Charles Lanyon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Charles Lanyon Context triple: [Crumlin Road Gaol, architect, Charles Lanyon]
-
A.
Alfred Harker
Alfred Harker was a British geologist and petrologist renowned for his pioneering work on igneous rocks and the geology of the British Isles.
-
B.
Nevil Macready
Nevil Macready was a British Army general best known for serving as Commander-in-Chief in Ireland during the Irish War of Independence.
-
C.
Henry Markham
Henry Markham was an American politician who served as the 18th governor of California from 1891 to 1895.
-
D.
Richard Black
Richard Black is a relatively common personal name shared by multiple notable individuals across fields such as politics, music, and academia.
-
E.
George Philip Wells
George Philip Wells was a British zoologist and author, known both for his scientific work and as the son of writer H. G. Wells.
- 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: Charles Lanyon Triple: [Crumlin Road Gaol, architect, Charles Lanyon]
Generated description
Charles Lanyon was a prominent 19th-century Irish architect known for designing many notable public buildings in Belfast and across Ulster.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Charles Lanyon Target entity description: Charles Lanyon was a prominent 19th-century Irish architect known for designing many notable public buildings in Belfast and across Ulster.
-
A.
Alfred Harker
Alfred Harker was a British geologist and petrologist renowned for his pioneering work on igneous rocks and the geology of the British Isles.
-
B.
Nevil Macready
Nevil Macready was a British Army general best known for serving as Commander-in-Chief in Ireland during the Irish War of Independence.
-
C.
Henry Markham
Henry Markham was an American politician who served as the 18th governor of California from 1891 to 1895.
-
D.
Richard Black
Richard Black is a relatively common personal name shared by multiple notable individuals across fields such as politics, music, and academia.
-
E.
George Philip Wells
George Philip Wells was a British zoologist and author, known both for his scientific work and as the son of writer H. G. Wells.
- 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_69a493599a0081908da65f3407af1ef2 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a64ecadc8190a82e25444e7abba6 |
completed | March 1, 2026, 8:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a76d767e5c8190918d55df7528f465 |
completed | March 3, 2026, 11:23 p.m. |
| NEDg | Description generation | batch_69a7727d46f08190a634f4fecb00b33c |
completed | March 3, 2026, 11:45 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69a774080e24819085b7cdd8e80c74b6 |
completed | March 3, 2026, 11:51 p.m. |
Created at: March 1, 2026, 7:37 p.m.