Triple
T11845362
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NoMad |
E281759
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | Gramercy |
E87520
|
NE FINISHED |
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: Gramercy | Statement: [NoMad, adjacentTo, Gramercy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gramercy Context triple: [NoMad, adjacentTo, Gramercy]
-
A.
Gramercy
chosen
Gramercy is an upscale, historic neighborhood on Manhattan’s east side, known for its elegant brownstones, tree-lined streets, and the private Gramercy Park.
-
B.
Fort Greene
Fort Greene is a historic and culturally vibrant neighborhood in Brooklyn, New York City, known for its brownstone-lined streets, diverse community, and proximity to cultural institutions and parks.
-
C.
Nolita
Nolita is a trendy, upscale neighborhood in Lower Manhattan known for its boutique shopping, stylish restaurants, and historic, narrow streets.
-
D.
Hudson Square
Hudson Square is a neighborhood on Manhattan’s west side known for its former industrial buildings, media and tech offices, and proximity to the Hudson River.
-
E.
Flatiron
Flatiron is a major North American construction firm known for building large-scale infrastructure projects such as bridges, highways, and transit systems.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d6ab287ba48190a5178779fd19b9b7 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a65b5ff08190bb58361f6a6acdca |
completed | April 10, 2026, 7:27 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f43fb078148190bdd7f36c6b292670 |
completed | May 1, 2026, 5:52 a.m. |
Created at: April 8, 2026, 9:43 p.m.