Triple
T20970691
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Two Union Square |
E516483
|
entity |
| Predicate | architect |
P184
|
FINISHED |
| Object | NBBJ |
—
|
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: NBBJ | Statement: [Two Union Square, architect, NBBJ]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: NBBJ Context triple: [Two Union Square, architect, NBBJ]
-
A.
NBBJ
chosen
NBBJ is a global architecture and design firm known for creating high-profile sports arenas, corporate campuses, and healthcare facilities.
-
B.
Chermayeff & Geismar
Chermayeff & Geismar is a renowned American graphic design firm best known for creating iconic corporate logos and visual identities for major global brands.
-
C.
HOK Group
HOK Group is a global design, architecture, engineering, and planning firm known for large-scale commercial, civic, and sports projects.
-
D.
Bohlin Cywinski Jackson
Bohlin Cywinski Jackson is an American architecture firm renowned for its innovative, minimalist designs for high-profile clients, including numerous iconic Apple retail stores.
-
E.
Perkins+Will
Perkins+Will is a global architecture and design firm known for its innovative, sustainable projects across sectors such as education, healthcare, and cultural institutions.
- 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_69e0b4fee5ac8190875fa9ceba1a5e5e |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fba027708190a49e95b0031d980d |
completed | April 21, 2026, 4:22 a.m. |
Created at: April 16, 2026, 1:43 p.m.