Triple
T16745429
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mark Parkinson |
E406938
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Mark Parkinson |
E406938
|
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: Mark Parkinson | Statement: [Mark Parkinson, name, Mark Parkinson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Parkinson Context triple: [Mark Parkinson, name, Mark Parkinson]
-
A.
Mark Parkinson
chosen
Mark Parkinson is an American politician who served as the 45th Governor of Kansas from 2009 to 2011.
-
B.
Joe Parkinson
Joe Parkinson is an American businessman best known as a co-founder and early leader of the semiconductor company Micron Technology.
-
C.
Ben Parkinson
Ben Parkinson is a former British paratrooper and one of the most severely injured soldiers to survive the Afghanistan conflict, widely recognized for his resilience and extensive charity work for wounded veterans.
-
D.
Craig Parkinson
Craig Parkinson is a British actor best known for his role as DI Matthew "Dot" Cottan in the television series "Line of Duty."
-
E.
Ward Parkinson
Ward Parkinson is an American engineer and entrepreneur best known as a co-founder of the semiconductor company Micron Technology.
- 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_69d8838ffb088190a0b11149929006bf |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3aa223aa88190a3c1805ece7317e2 |
completed | April 18, 2026, 3:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00a52033748190ae207d72d437236b |
completed | May 10, 2026, 3:32 p.m. |
Created at: April 10, 2026, 5:21 a.m.