Triple
T10368914
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom Patterson Island |
E244324
|
entity |
| Predicate | isNamedAfter |
P63
|
FINISHED |
| Object |
Tom Patterson
Tom Patterson was a Canadian theatre producer best known as the founder of the Stratford Festival in Ontario.
|
E858830
|
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: Tom Patterson | Statement: [Tom Patterson Island, isNamedAfter, Tom Patterson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tom Patterson Context triple: [Tom Patterson Island, isNamedAfter, Tom Patterson]
-
A.
Bob McGrew
Bob McGrew is a computer scientist and researcher known for co-authoring the Hindsight Experience Replay technique in reinforcement learning.
-
B.
Jeff Tarpley
Jeff Tarpley is an American actor best known to the public as the ex-husband of comedian and television personality Sherri Shepherd.
-
C.
John P. Burke
John P. Burke was a public official who served as New York State's Industrial Commissioner, overseeing labor and industry-related policies and regulations.
-
D.
James Nourse
James Nourse was an 18th-century British sea captain involved in the transatlantic slave trade.
-
E.
William Gillespie
William Gillespie was a Scottish-born character actor of the silent and early sound film era, known for his supporting roles in numerous comedies, including those produced by Hal Roach.
- 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: Tom Patterson Triple: [Tom Patterson Island, isNamedAfter, Tom Patterson]
Generated description
Tom Patterson was a Canadian theatre producer best known as the founder of the Stratford Festival in Ontario.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tom Patterson Target entity description: Tom Patterson was a Canadian theatre producer best known as the founder of the Stratford Festival in Ontario.
-
A.
Bob McGrew
Bob McGrew is a computer scientist and researcher known for co-authoring the Hindsight Experience Replay technique in reinforcement learning.
-
B.
Jeff Tarpley
Jeff Tarpley is an American actor best known to the public as the ex-husband of comedian and television personality Sherri Shepherd.
-
C.
John P. Burke
John P. Burke was a public official who served as New York State's Industrial Commissioner, overseeing labor and industry-related policies and regulations.
-
D.
James Nourse
James Nourse was an 18th-century British sea captain involved in the transatlantic slave trade.
-
E.
William Gillespie
William Gillespie was a Scottish-born character actor of the silent and early sound film era, known for his supporting roles in numerous comedies, including those produced by Hal Roach.
- 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_69d381b3e328819094b23b8edcd29b5a |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e9725fa08190816bedf0acefbc2a |
completed | April 7, 2026, 11:24 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d79550b2ec8190ada086ddfeb398af |
completed | April 9, 2026, 12:02 p.m. |
| NEDg | Description generation | batch_69d7985e7fc081909fd1ba1dc6f7338c |
completed | April 9, 2026, 12:15 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d799917ab881909a947ad8059652c6 |
completed | April 9, 2026, 12:20 p.m. |
Created at: April 6, 2026, 12:01 p.m.