Triple
T26706421
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coliidae |
E673297
|
entity |
| Predicate | thermalBehavior |
P111609
|
FINISHED |
| Object | huddling for warmth |
—
|
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: huddling for warmth | Statement: [Coliidae, thermalBehavior, huddling for warmth]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: thermalBehavior Context triple: [Coliidae, thermalBehavior, huddling for warmth]
-
A.
thermalProperty
chosen
Indicates a relationship where an entity is associated with a characteristic describing its behavior or response with respect to temperature or heat.
-
B.
thermalComplex
Indicates a relationship where entities are associated through a thermal interaction, structure, or system forming a combined thermal complex.
-
C.
temperatureDependent
Indicates that the existence, intensity, or outcome of a relationship or process varies as a function of temperature.
-
D.
thermalEffect
Indicates a relationship where one entity causes or experiences a change related to heat, such as temperature increase, decrease, or transfer, due to another entity or process.
-
E.
thermalStateFor
Indicates a relationship where one entity specifies or defines the thermal condition or temperature-related state of 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_69eecda2b49c8190a6c481cfc4c07954 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f61a17a7788190946f7e32d63cd43f |
completed | May 2, 2026, 3:36 p.m. |
| PD | Predicate disambiguation | batch_69f611ab768c8190b1849c15a3e59dda |
completed | May 2, 2026, 3 p.m. |
Created at: April 27, 2026, 3:34 a.m.