Triple
T7975788
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | York, Pennsylvania |
E185442
|
entity |
| Predicate | founder |
P104
|
FINISHED |
| Object | Thomas Cookson |
E249993
|
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: Thomas Cookson | Statement: [York, Pennsylvania, founder, Thomas Cookson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thomas Cookson Context triple: [York, Pennsylvania, founder, Thomas Cookson]
-
A.
Thomas Cookson
chosen
Thomas Cookson was an early settler and civic leader credited with establishing the city of York in Pennsylvania.
-
B.
Henry Cooke
Henry Cooke is a notable individual distinguished enough to be recognized as a prominent bearer of the surname Cooke.
-
C.
Thomas Cooke
Thomas Cooke is a relatively common English personal name shared by multiple historical and contemporary figures across various professions.
-
D.
William Jessop
William Jessop was a prominent 18th-century English civil engineer known for his influential work on canals, docks, and early railways during the Industrial Revolution.
-
E.
Richard Suckle
Richard Suckle is an American film producer known for his work on major studio projects, including the DC superhero film "Wonder Woman" (2017).
- 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_69ca829851908190b4e03829353ee7c3 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3bf56f688190902b95afe42635ec |
completed | March 31, 2026, 3:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cbe0c39e248190a146c1f2fd815f26 |
completed | March 31, 2026, 2:57 p.m. |
Created at: March 30, 2026, 5:14 p.m.