Triple
T9911949
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Port Sunlight |
E185163
|
entity |
| Predicate | hasArchitect |
P184
|
FINISHED |
| Object | John Douglas |
E636762
|
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 Douglas | Statement: [Port Sunlight, hasArchitect, John Douglas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Douglas Context triple: [Port Sunlight, hasArchitect, John Douglas]
-
A.
John Douglas
chosen
John Douglas was a prominent 19th-century English architect known for his distinctive Victorian and Gothic Revival designs, particularly in and around Chester.
-
B.
John Douglas
John Douglas was a 16th-century Scottish minister and theologian who helped shape early Scottish Protestant doctrine as one of the authors of the Scots Confession.
-
C.
John Krueger
John Krueger is an American mathematician known for his work in set theory and related areas of mathematical logic.
-
D.
Michael Ripps
Michael Ripps is a film editor known for his work on the movie "Stakeout."
-
E.
John Munch
John Munch is a cynical, conspiracy-minded detective portrayed by Richard Belzer, best known for his long-running cross-series role in the Law & Order and Homicide television franchises.
- 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_69ca8296165881908ca4750701af1f29 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cdb5391b8081908094b88cdde4b55a |
completed | April 2, 2026, 12:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d20dcbf28c8190aa9f6a8be423670a |
completed | April 5, 2026, 7:22 a.m. |
Created at: March 30, 2026, 8:41 p.m.