Triple
T20454743
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ratargul Swamp Forest |
E501745
|
entity |
| Predicate | localNameOfCommonTree |
P1354
|
FINISHED |
| Object | Koroch |
—
|
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: Koroch | Statement: [Ratargul Swamp Forest, localNameOfCommonTree, Koroch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: localNameOfCommonTree Context triple: [Ratargul Swamp Forest, localNameOfCommonTree, Koroch]
-
A.
dominantTreeCommonName
Indicates the common (non-scientific) name of the tree species that is dominant in a given area or ecological context.
-
B.
hasSurroundingTreeCommonName
Indicates that an entity is associated with a surrounding tree identified by its common (vernacular) name.
-
C.
commonNameOf
chosen
Indicates that one entity is the commonly used or popular name by which the other entity is known.
-
D.
modernLocalName
Indicates the current, locally used name or designation for an entity, as recognized in the present time.
-
E.
localNameDefinition
Indicates that an entity’s locally scoped name is defined or specified within a particular context or namespace.
- 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_69e0b4ad4940819098cf2ff6413574e5 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e68d04ca4081909b428c31d16fca10 |
completed | April 20, 2026, 8:31 p.m. |
| PD | Predicate disambiguation | batch_69e57679eb40819086142df3e39c928e |
completed | April 20, 2026, 12:42 a.m. |
Created at: April 16, 2026, 11:32 a.m.