Triple
T4291184
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | California tiger salamander |
E99594
|
entity |
| Predicate | spendsMostOfLife |
P18931
|
FINISHED |
| Object | underground |
—
|
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: underground | Statement: [California tiger salamander, spendsMostOfLife, underground]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spendsMostOfLife Context triple: [California tiger salamander, spendsMostOfLife, underground]
-
A.
spentMostOfLifeIn
chosen
Indicates that an entity resided or was primarily based in a particular place for the majority of its lifetime.
-
B.
living
Indicates that an entity is alive or currently exists in a living state.
-
C.
lifeHabit
Indicates the typical way an organism lives or behaves in its environment, such as its mode of life, activity pattern, or ecological lifestyle.
-
D.
lifeStatus
Indicates the current state of an entity’s existence, such as whether it is alive, dead, or in another defined life condition.
-
E.
followsLifeOf
Indicates that one entity’s narrative, development, or progression is tracked or depicted over the course of that entity’s life.
- 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_69b3455175088190aa79c6e03b86647e |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3507efb28819091a9d5b9161a5008 |
completed | March 12, 2026, 11:47 p.m. |
| PD | Predicate disambiguation | batch_69b347fc4c0c8190a7fcd814e27308a5 |
completed | March 12, 2026, 11:10 p.m. |
Created at: March 12, 2026, 11:08 p.m.