Triple
T24100993
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arthur Kill shoreline |
E597071
|
entity |
| Predicate | formsPartOfCoastOf |
P60480
|
FINISHED |
| Object | Tottenville neighborhood |
—
|
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: Tottenville neighborhood | Statement: [Arthur Kill shoreline, formsPartOfCoastOf, Tottenville neighborhood]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formsPartOfCoastOf Context triple: [Arthur Kill shoreline, formsPartOfCoastOf, Tottenville neighborhood]
-
A.
isPartOfCoastOf
chosen
Indicates that one entity forms a segment or component of the coastline belonging to another entity.
-
B.
isCoastalSettlementOf
Indicates that a settlement is located on or near the coast within the territory of a specified geographic or administrative area.
-
C.
countryCoastlineOf
Indicates that a country has the specified coastline as part of its national territory or boundary.
-
D.
includesCoastOf
Indicates that one geographic or administrative entity encompasses or contains the coastline of another entity.
-
E.
hasCountryCoastlineOn
Indicates that a country has a coastline bordering a specified body of water or sea.
- F. None of above.
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_69e288c548048190a5c1018da1166a21 |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1dd28d6a08190b6d513f774973050 |
completed | April 29, 2026, 10:27 a.m. |
| PD | Predicate disambiguation | batch_69f17651458c8190bbfd301883e46085 |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 11 p.m.