Triple
T10891853
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Satsuma mandarins |
E257195
|
entity |
| Predicate | coldTolerance |
P1349
|
FINISHED |
| Object | relatively cold-hardy for citrus |
—
|
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: relatively cold-hardy for citrus | Statement: [Satsuma mandarins, coldTolerance, relatively cold-hardy for citrus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coldTolerance Context triple: [Satsuma mandarins, coldTolerance, relatively cold-hardy for citrus]
-
A.
isColderThan
Indicates that one entity has a lower temperature than another entity.
-
B.
winterTemperatureRange_C
Indicates the range of temperatures, in degrees Celsius, typically experienced during the winter season for the subject.
-
C.
hasTemperatureRegime
Indicates that an entity is characterized by or associated with a particular pattern or regime of temperature conditions.
-
D.
freezesOver
Indicates that a liquid surface becomes solid due to low temperatures, typically forming a layer of ice over it.
-
E.
hardiness
chosen
Indicates the degree to which an entity can withstand or endure harsh, adverse, or challenging conditions.
- 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_69d6aa8550c8819095508a2ed9acf3db |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d75206354881908b148f2df3938513 |
completed | April 9, 2026, 7:15 a.m. |
| PD | Predicate disambiguation | batch_69d70d3943c881908895397eccc3e415 |
completed | April 9, 2026, 2:21 a.m. |
Created at: April 8, 2026, 9:21 p.m.