Triple
T14946379
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Welsh-Ryan Arena |
E372672
|
entity |
| Predicate | namedAfter |
P63
|
FINISHED |
| Object | Patrick G. Ryan |
E1166772
|
NE FINISHED |
How this triple was built (2 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: Patrick G. Ryan | Statement: [Welsh-Ryan Arena, namedAfter, Patrick G. Ryan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Patrick G. Ryan Context triple: [Welsh-Ryan Arena, namedAfter, Patrick G. Ryan]
-
A.
Patrick G. Ryan
chosen
Patrick G. Ryan is an American businessman and philanthropist best known as the founder of Aon Corporation and a major benefactor of Northwestern University.
-
B.
John P. Ryan
John P. Ryan was an American character actor known for his intense performances in film and television, often portraying tough or villainous roles.
-
C.
William F. O’Connor
William F. O’Connor was an Irish political figure who succeeded Tomás Mac Curtain in office, likely in a local governmental role in Cork during the early 20th century.
-
D.
Thomas J. Sheehan
Thomas J. Sheehan was a U.S. Army officer best known for leading the defense of Fort Ridgely during the U.S.–Dakota War of 1862.
-
E.
John A. Byrne
John A. Byrne is an American business journalist and author best known for his work covering corporate leadership and management, including co-authoring high-profile business books.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d85cca979481908747d2a81eba1cea |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded68e35c481908e47cd68441c5115 |
completed | April 15, 2026, 12:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff6ec12de8819097cd83530e54f54b |
completed | May 9, 2026, 5:28 p.m. |
Created at: April 10, 2026, 2:39 a.m.