Triple
T8726468
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Union Station (Los Angeles) |
E207142
|
entity |
| Predicate | architect |
P184
|
FINISHED |
| Object | John Parkinson |
E53828
|
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: John Parkinson | Statement: [Union Station (Los Angeles), architect, John Parkinson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Parkinson Context triple: [Union Station (Los Angeles), architect, John Parkinson]
-
A.
John Parkinson
chosen
John Parkinson was a prominent early 20th-century architect known for shaping the skyline of Los Angeles with landmark civic and commercial buildings.
-
B.
John Parkinson
John Parkinson was a notable English botanist and herbalist of the early 17th century, renowned for his influential plant catalogues and contributions to horticulture.
-
C.
Robert Barker
Robert Barker was a 17th-century English royal printer best known for printing the first edition of the King James Bible.
-
D.
John Davies
John Davies was a British Conservative politician and businessman who served in senior government roles during the late 1960s and early 1970s.
-
E.
Thomas Hatfield
Thomas Hatfield was a 14th-century Bishop of Durham and influential English cleric and statesman.
- 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_69ca835811d8819081ea00fd2a2c9a1c |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5d16cba881908e2a14b60ae65524 |
completed | March 31, 2026, 11:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cf2912c4e08190a147fc31db6788d1 |
completed | April 3, 2026, 2:42 a.m. |
Created at: March 30, 2026, 6:36 p.m.