Triple
T21241078
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Great Glasshouse |
E523472
|
entity |
| Predicate | architect |
P184
|
FINISHED |
| Object | Norman Foster |
—
|
NE NERFINISHED |
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: Norman Foster | Statement: [Great Glasshouse, architect, Norman Foster]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Norman Foster Context triple: [Great Glasshouse, architect, Norman Foster]
-
A.
Norman Foster
chosen
Norman Foster is a renowned British architect known for his high-tech, innovative designs such as London's Gherkin and the Reichstag dome in Berlin.
-
B.
Norman Foster
Norman Foster was an American film and television director and actor active in Hollywood from the 1920s through the 1950s.
-
C.
Richard Rogers
Richard Rogers was a renowned British architect celebrated for his high-tech, modernist designs, including the Centre Pompidou in Paris and the Lloyd’s building in London.
-
D.
Richard Rogers
Richard Rogers is the son of Mary Kay Ash, the founder of Mary Kay Cosmetics, and has been involved in the leadership of the company.
-
E.
David Chipperfield
David Chipperfield is a renowned British architect celebrated for his minimalist, modernist designs and influential cultural and civic projects worldwide.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b513b89c81908b27147e91368db2 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e735239f48819091ffe518b1aed2e8 |
completed | April 21, 2026, 8:28 a.m. |
Created at: April 16, 2026, 3:47 p.m.