Triple
T20756735
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Soho Square Gardens |
E510868
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Greek Street |
—
|
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: Greek Street | Statement: [Soho Square Gardens, near, Greek Street]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Greek Street Context triple: [Soho Square Gardens, near, Greek Street]
-
A.
Greek Street
chosen
Greek Street is a notable thoroughfare in London’s Soho district, known for its historic buildings, restaurants, and vibrant nightlife.
-
B.
Athinas Street
Athinas Street is a central thoroughfare in Athens, Greece, known for its traditional markets, shops, and direct link between Omonoia Square and Monastiraki.
-
C.
Teatinos Street
Teatinos Street is a central thoroughfare in downtown Santiago, Chile, known for its proximity to key government buildings and historic city landmarks.
-
D.
Adrianou Street
Adrianou Street is a historic pedestrian thoroughfare in central Athens, Greece, known for its shops, cafés, and views of ancient sites like the Acropolis.
-
E.
Vasina Street
Vasina Street is a central street in Belgrade’s Stari Grad municipality, known for its proximity to key landmarks such as Republic Square and the University of Belgrade.
- 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_69e0b4c909ec8190b05987f1639513f6 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c23113c88190a567c3a098cf7552 |
completed | April 21, 2026, 12:17 a.m. |
Created at: April 16, 2026, 12:35 p.m.