Triple
T5350481
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Malayan sun bear |
E124164
|
entity |
| Predicate | secondaryHabitat |
P50917
|
FINISHED |
| Object | montane forest |
—
|
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: montane forest | Statement: [Malayan sun bear, secondaryHabitat, montane forest]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secondaryHabitat Context triple: [Malayan sun bear, secondaryHabitat, montane forest]
-
A.
secondaryEnvironment
chosen
Indicates that an entity is associated with an additional or supporting environment distinct from its primary one.
-
B.
secondaryLandUse
Indicates a secondary or additional way in which a piece of land is used, beyond its primary designated use.
-
C.
secondaryIsland
Indicates that one island is a secondary or subordinate island in relation to a primary or main island.
-
D.
secondaryTo
Indicates that one condition, event, or factor occurs as a consequence of, or is caused by, another primary condition, event, or factor.
-
E.
featuresHabitat
Indicates that something includes or provides a particular habitat as part of its characteristics or environment.
- 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_69bd464be27081908807b40b75c1bbae |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd860fe4048190846a933d0e1b9386 |
completed | March 20, 2026, 5:38 p.m. |
| PD | Predicate disambiguation | batch_69bd845c6f108190832a8d14b356368a |
completed | March 20, 2026, 5:31 p.m. |
Created at: March 20, 2026, 2:01 p.m.