Triple
T31695009
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Greenpoint Avenue ferry landing |
E808893
|
entity |
| Predicate | hasNearbyBoroughBorder |
P198854
|
FINISHED |
| Object | Brooklyn–Queens boundary |
—
|
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: Brooklyn–Queens boundary | Statement: [Greenpoint Avenue ferry landing, hasNearbyBoroughBorder, Brooklyn–Queens boundary]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNearbyBoroughBorder Context triple: [Greenpoint Avenue ferry landing, hasNearbyBoroughBorder, Brooklyn–Queens boundary]
-
A.
hasNearbyBorough
Indicates that one borough is geographically close to or adjacent to another borough.
-
B.
hasBoroughBorderContext
Indicates that a borough is contextually related to or influenced by the borders it shares with neighboring boroughs or areas.
-
C.
hasNearbyCountyBorder
Indicates that the borders of two counties are geographically close to each other, though not necessarily directly adjacent.
-
D.
hasAdjacentBoroughHallConnection
Indicates that there is a direct, neighboring connection between a location and a borough hall.
-
E.
hasBoroughHallVicinity
Indicates that an entity is located in the area surrounding or in close proximity to a borough hall.
- F. None of above. chosen
Provenance (4 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_69f348ddcbc48190950cabcc25ff29b3 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69ff0e9c75208190a4423261f00b79b3 |
completed | May 9, 2026, 10:38 a.m. |
| PD | Predicate disambiguation | batch_69ff0e07f08481909c4ae322632a6bf0 |
completed | May 9, 2026, 10:35 a.m. |
| PDg | Predicate description generation | batch_69ff0e9b7acc81909a0ee66201a06877 |
completed | May 9, 2026, 10:38 a.m. |
Created at: April 30, 2026, 11:10 p.m.