Triple
T14668799
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rocky Point (Saint Thomas, Jamaica) |
E344451
|
entity |
| Predicate | hasCoastalForm |
P5879
|
FINISHED |
| Object | headland |
—
|
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: headland | Statement: [Rocky Point (Saint Thomas, Jamaica), hasCoastalForm, headland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCoastalForm Context triple: [Rocky Point (Saint Thomas, Jamaica), hasCoastalForm, headland]
-
A.
hasCoastalCharacteristic
Indicates that an entity possesses a feature, quality, or condition specifically related to coastal or shoreline environments.
-
B.
hasCoastalSection
Indicates that a geographic entity includes at least one section of land that directly borders a sea or ocean.
-
C.
containsCoastalFeature
chosen
Indicates that one entity geographically includes or encompasses a coastal feature (such as a beach, cliff, bay, or shoreline) within its area or boundaries.
-
D.
hasCoastalPath
Indicates that there exists a designated path or route running along or adjacent to the coastline of a given area or feature.
-
E.
hasCoastalRegion
Indicates that a place possesses at least one region that borders or is directly adjacent to a sea or ocean.
- 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_69d822e283fc8190a0e4c235cf880052 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb54dda1c8190bf16d17e26a2bba6 |
completed | April 14, 2026, 9:44 p.m. |
| PD | Predicate disambiguation | batch_69de6576f0208190aa94d995e797ac38 |
completed | April 14, 2026, 4:04 p.m. |
Created at: April 10, 2026, 1:27 a.m.