Triple
T402026
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Biscayne National Park |
E9305
|
entity |
| Predicate | percentMarineArea |
P475
|
FINISHED |
| Object | about 95 percent |
—
|
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: about 95 percent | Statement: [Biscayne National Park, percentMarineArea, about 95 percent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: percentMarineArea Context triple: [Biscayne National Park, percentMarineArea, about 95 percent]
-
A.
marineArea
Indicates a relationship where an entity is located in, associated with, or relevant to a specific marine or oceanic area.
-
B.
coversFractionOfWorldOceanArea
Indicates that a specified entity accounts for a given fraction of the total surface area of the world’s oceans.
-
C.
appliesToSeaArea
Indicates that something (such as a rule, restriction, or designation) is relevant or valid within a specified sea area.
-
D.
areaWater
chosen
Indicates the relationship between a geographic entity and the total area of its surface that is covered by water.
-
E.
isShallowSea
Indicates that a body of water is a shallow marine area, typically near coasts or continental shelves, rather than deep 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_69a2e8004cb88190b92ed1add6abf41a |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2ec9f77888190bcc2bc68d201ed35 |
completed | Feb. 28, 2026, 1:24 p.m. |
| PD | Predicate disambiguation | batch_69a2e96ee4ec8190a5c0e3f491d3963d |
completed | Feb. 28, 2026, 1:11 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.