Triple
T8467565
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Urocitellus |
E200201
|
entity |
| Predicate | usesBurrowsFor |
P22634
|
FINISHED |
| Object | protection from predators |
—
|
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: protection from predators | Statement: [Urocitellus, usesBurrowsFor, protection from predators]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesBurrowsFor Context triple: [Urocitellus, usesBurrowsFor, protection from predators]
-
A.
burrowSystem
Indicates that one entity is a system or network of burrows associated with another entity.
-
B.
buriedFor
Indicates that one entity is buried on behalf of, in honor of, or as a memorial for another entity.
-
C.
isBuriedIn
Indicates that one entity is located beneath the ground or enclosed within another entity, typically as in a grave, tomb, or burial site.
-
D.
buriedUnder
Indicates that one entity is located beneath another entity in such a way that it is covered or concealed by it, as if buried.
-
E.
areUsedBy
chosen
Indicates that certain entities serve as tools, resources, or means that are utilized or employed by other entities.
- 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_69ca831a4f348190bfdd09250e86ae35 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe4d2eb648190b606411eb6a8f7ea |
completed | March 31, 2026, 3:14 p.m. |
| PD | Predicate disambiguation | batch_69cbd10072cc819084be1ed9ac7ebe9d |
completed | March 31, 2026, 1:49 p.m. |
Created at: March 30, 2026, 6:11 p.m.