Triple
T29668485
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wakefield, Bronx |
E750599
|
entity |
| Predicate | southernNeighbor |
P9676
|
FINISHED |
| Object | Edenwald, Bronx |
—
|
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: Edenwald, Bronx | Statement: [Wakefield, Bronx, southernNeighbor, Edenwald, Bronx]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: southernNeighbor Context triple: [Wakefield, Bronx, southernNeighbor, Edenwald, Bronx]
-
A.
northernRegionAdjacentTo
Indicates that one region is directly next to another and lies to its north.
-
B.
adjacentCitySouth
Indicates that one city is directly to the south of another city, sharing a common boundary or being immediately neighboring in that direction.
-
C.
hasNeighboringStateToWest
Indicates that one state is geographically located directly to the west of another state, sharing a common border.
-
D.
hasNeighboringCountryToNorth
Indicates that one country is directly adjacent to and located south of another country, which lies to its north.
-
E.
locatedSouthOf
chosen
Indicates that one entity is positioned geographically to the south of another entity.
- 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_69f0d62418a08190a401b127adf9f8a6 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f671c5d3308190b78b458b37ee5e47 |
completed | May 2, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69f6659f246081909821c5f452d14e8f |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 7:02 p.m.