Triple
T10357510
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fifth Avenue and 105th Street |
E244036
|
entity |
| Predicate | locatedOnEdgeOf |
P67212
|
FINISHED |
| Object | Central Park eastern edge |
—
|
LITERAL 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: Central Park eastern edge | Statement: [Fifth Avenue and 105th Street, locatedOnEdgeOf, Central Park eastern edge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedOnEdgeOf Context triple: [Fifth Avenue and 105th Street, locatedOnEdgeOf, Central Park eastern edge]
-
A.
isLocatedOnOutskirtsOf
Indicates that one entity is situated on the outer edge or peripheral area of another entity, rather than in its central or inner part.
-
B.
locatedAtCornerOf
Indicates that one entity is positioned at or forms the corner where two or more boundaries, edges, or intersecting paths meet.
-
C.
liesOnBorderOf
chosen
Indicates that one entity is located along or directly adjacent to the boundary line separating it from another entity.
-
D.
formsEdgeOf
Indicates that one entity constitutes a boundary or outer limit of another entity.
-
E.
locatedAlong
Indicates that one entity is situated adjacent to, or running beside, the length or course of another linear feature (such as a road, river, or railway).
- 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_69d381b22b8c8190aaed476be5f872a9 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e9563ea48190b8702b3ef497ed9a |
completed | April 7, 2026, 11:24 a.m. |
| PD | Predicate disambiguation | batch_69d4dfa657f481909cc5cc8fec00ad19 |
completed | April 7, 2026, 10:42 a.m. |
Created at: April 6, 2026, 11:58 a.m.