Triple
T20364891
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rivergate Tower |
E496881
|
entity |
| Predicate | architect |
P184
|
FINISHED |
| Object | Harry Wolf |
—
|
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: Harry Wolf | Statement: [Rivergate Tower, architect, Harry Wolf]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harry Wolf Context triple: [Rivergate Tower, architect, Harry Wolf]
-
A.
Harry Wolf
chosen
Harry Wolf is an American architect known for his innovative, context-sensitive high-rise and urban designs.
-
B.
Harry DeWolf
Harry DeWolf was a distinguished Canadian naval officer and admiral best known for his World War II service commanding the destroyer HMCS Haida.
-
C.
Tim McAuliffe
Tim McAuliffe is a Canadian television writer and producer known for his work on comedy series such as "The Office," "Last Man on Earth," and "Late Night with Jimmy Fallon."
-
D.
Larry Wolf
Larry Wolf is an individual notable enough to be recognized as a prominent bearer of the surname Wolf, though specific widely known achievements or roles are not clearly established from this context alone.
-
E.
Philip DeGuard
Philip DeGuard was an American animation background artist best known for his richly detailed and stylized work on classic Warner Bros. cartoons.
- 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_69e0b4a4f9b081908a5a021919c21ccb |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67870f4448190ab63cbe03542de21 |
completed | April 20, 2026, 7:03 p.m. |
Created at: April 16, 2026, 11:26 a.m.