Triple
T30410272
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Restinga da Marambaia (partially) |
E773597
|
entity |
| Predicate | isPartOfBiome |
P110631
|
FINISHED |
| Object | Atlantic Forest biome |
—
|
NE NERFINISHED |
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: Atlantic Forest biome | Statement: [Restinga da Marambaia (partially), isPartOfBiome, Atlantic Forest biome]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isPartOfBiome Context triple: [Restinga da Marambaia (partially), isPartOfBiome, Atlantic Forest biome]
-
A.
isLocatedInBiome
chosen
Indicates that one entity is situated within or belongs to the environmental region or biome represented by another entity.
-
B.
biomeIncludes
Indicates that a biome contains or encompasses a particular entity, such as a species, habitat, or environmental feature, as part of its composition.
-
C.
hasSecondaryBiome
Indicates that an entity is associated with an additional, subordinate biome type beyond its primary biome.
-
D.
addsBiome
Indicates that one entity introduces or associates a new biome with another entity.
-
E.
isOuterEndBiome
Indicates that a biome is located at the outer edge or boundary region of the End dimension.
- 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_69f22490b8b48190ab10c886a8d58c89 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fdee770af48190aca2670db50f8b49 |
completed | May 8, 2026, 2:08 p.m. |
| PD | Predicate disambiguation | batch_69fdecec98a08190a357d816dc2a6dbe |
completed | May 8, 2026, 2:02 p.m. |
Created at: April 29, 2026, 8:04 p.m.