Triple
T18369290
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sea otter |
E440136
|
entity |
| Predicate | insulationMethod |
P93512
|
FINISHED |
| Object | fur rather than blubber |
—
|
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: fur rather than blubber | Statement: [Sea otter, insulationMethod, fur rather than blubber]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: insulationMethod Context triple: [Sea otter, insulationMethod, fur rather than blubber]
-
A.
insulation
chosen
Indicates that one entity serves as a barrier reducing the transfer of heat, sound, or electricity between itself and another entity or environment.
-
B.
waterproofingMethod
Indicates the technique or process used to make an object, surface, or structure resistant to water penetration.
-
C.
heatTransferMethod
Indicates the mechanism or process by which heat is transferred from one entity or system to another.
-
D.
soundInsulation
Indicates the degree to which one entity reduces or blocks the transmission of sound from another entity or environment.
-
E.
heatingMethod
Indicates the method or technique used to apply heat to something, such as for cooking, warming, or processing.
- 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_69d8b918221c8190a9f7b563d64ac677 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e51750d3dc8190b153046c1171ee2b |
completed | April 19, 2026, 5:56 p.m. |
| PD | Predicate disambiguation | batch_69e44fed3fdc81908f4ed6a81db42416 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:38 a.m.