Triple
T18298078
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Import Dock |
E438284
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | Poplar |
—
|
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: Poplar | Statement: [Import Dock, adjacentTo, Poplar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Poplar Context triple: [Import Dock, adjacentTo, Poplar]
-
A.
Poplar
chosen
Poplar is a historic district in the East End of London known for its docklands heritage, post-war social housing, and proximity to Canary Wharf.
-
B.
Poplar
Poplar is a small rural community located within the township of Central Manitoulin in Ontario, Canada.
-
C.
West Poplar
West Poplar is a residential neighborhood in Philadelphia, Pennsylvania, known for its rowhouses, community redevelopment, and proximity to Center City.
-
D.
Populus
Populus is a genus of fast-growing deciduous trees commonly known as poplars, aspens, and cottonwoods, widespread across the Northern Hemisphere.
-
E.
Davie Poplar
Davie Poplar is a historic, centuries-old tulip poplar tree on the campus of the University of North Carolina at Chapel Hill and a well-known campus symbol and gathering spot.
- 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_69d8b915e3e881909125d760c15d0c29 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e5017cc540819096c103a2c72315e6 |
completed | April 19, 2026, 4:23 p.m. |
Created at: April 10, 2026, 10:35 a.m.