Triple
T10881230
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | African Elephant Crossing |
E256921
|
entity |
| Predicate | hasHabitatZone |
P31280
|
FINISHED |
| Object | savanna zone |
—
|
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: savanna zone | Statement: [African Elephant Crossing, hasHabitatZone, savanna zone]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHabitatZone Context triple: [African Elephant Crossing, hasHabitatZone, savanna zone]
-
A.
containsSpeciesWithHabitat
Indicates that an entity includes one or more species that are associated with a particular habitat.
-
B.
simulatesHabitatOf
Indicates that one entity artificially recreates or models the living conditions or environment characteristic of another entity’s natural habitat.
-
C.
isEcologicalZone
chosen
Indicates that one entity functions as, or is classified as, an ecological zone in relation to another entity.
-
D.
hasNearbyHabitats
Indicates that one entity has other habitats located close to it in geographic or spatial terms.
-
E.
isMajorHabitatFor
Indicates that one entity serves as a primary or significant natural living environment for another entity.
- 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_69d6aa848804819081b2713ca0bedf06 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d751b031a88190b1182dfc1f520264 |
completed | April 9, 2026, 7:13 a.m. |
| PD | Predicate disambiguation | batch_69d70d360c388190a3d829fe8862434f |
completed | April 9, 2026, 2:21 a.m. |
Created at: April 8, 2026, 9:21 p.m.