Triple
T5416417
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eastern gray squirrel |
E121143
|
entity |
| Predicate | hasLifespanInCaptivity |
P49304
|
FINISHED |
| Object | up to 20 years |
—
|
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: up to 20 years | Statement: [Eastern gray squirrel, hasLifespanInCaptivity, up to 20 years]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLifespanInCaptivity Context triple: [Eastern gray squirrel, hasLifespanInCaptivity, up to 20 years]
-
A.
lifePeriod
Indicates the span of time during which an entity exists, is active, or is valid.
-
B.
reproductionInCaptivity
Indicates that an organism reproduces successfully while being kept in a controlled or captive environment rather than in the wild.
-
C.
lifespan
Indicates the duration of time between an entity’s birth (or creation) and its death (or end).
-
D.
maximumRecordedLifespan
chosen
Indicates the greatest length of time that has ever been recorded for an individual of a given type to live.
-
E.
hasWildPopulationOf
Indicates that a location or area contains a naturally occurring, non-captive population of the specified species.
- 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_69bd463a41cc8190b32ff5af2b96ca93 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd87bff75881909bdfd2cdf7ff5657 |
completed | March 20, 2026, 5:45 p.m. |
| PD | Predicate disambiguation | batch_69bd8469f5e48190bbe5c8bdfe8925ea |
completed | March 20, 2026, 5:31 p.m. |
Created at: March 20, 2026, 2:05 p.m.