Triple
T3373107
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marcus Garvey Park |
E70999
|
entity |
| Predicate | hasTopographicalFeature |
P940
|
FINISHED |
| Object | rocky hill |
—
|
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: rocky hill | Statement: [Marcus Garvey Park, hasTopographicalFeature, rocky hill]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTopographicalFeature Context triple: [Marcus Garvey Park, hasTopographicalFeature, rocky hill]
-
A.
hasLandform
chosen
Indicates that one entity possesses, contains, or is characterized by a particular natural landform.
-
B.
terrainFeature
Indicates a relationship where one entity is a natural or constructed landform or surface characteristic associated with a given location or area.
-
C.
hasNaturalFeature
Indicates that one entity possesses, contains, or is characterized by a particular natural feature (such as a mountain, river, forest, or coastline).
-
D.
topographyBasedOn
Indicates that the topographical characteristics of one entity are derived from, determined by, or modeled using the topography of another entity.
-
E.
hasMountainousTerrain
Indicates that a location or area possesses predominantly mountainous physical terrain or landscape features.
- 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_69ad85a7f80c8190a05e43013f298942 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb2bdcf70819087fc7e00fbd61e0d |
completed | March 8, 2026, 5:32 p.m. |
| PD | Predicate disambiguation | batch_69ada433059881908e46f38cc5f40a32 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:13 p.m.