Triple
T18684397
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Targ Węglowy |
E456818
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Długa 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: Długa Street | Statement: [Targ Węglowy, near, Długa Street]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Długa Street Context triple: [Targ Węglowy, near, Długa Street]
-
A.
Długa Street
chosen
Długa Street is a historic main thoroughfare in Gdańsk, Poland, known for its colorful townhouses, landmarks, and role as part of the Royal Route.
-
B.
Poland Street
Poland Street is a street in London’s Soho district, known for its central location and mix of shops, offices, and cultural venues.
-
C.
Rector Street
Rector Street is a street in Lower Manhattan, New York City, located in the Financial District near the southern tip of the island.
-
D.
Marymoncka Street
Marymoncka Street is a major thoroughfare in Warsaw’s Bielany district, known for connecting residential areas with key transport routes and local institutions.
-
E.
Nádor Street
Nádor Street is a central street in Budapest’s historic District V, known for its proximity to key government buildings, cultural institutions, and the Danube riverfront.
- 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_69d8d391eb488190ac2e9abf5bf255e4 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e55b2b819c8190b5f3d7a88607f6f5 |
completed | April 19, 2026, 10:46 p.m. |
Created at: April 10, 2026, 11:49 a.m.