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.