Triple
T38491853
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | culpeo |
E918072
|
entity |
| Predicate | bodySizeRelativeToOtherCanids |
P70596
|
FINISHED |
| Object | second-largest native canid in South America |
—
|
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: second-largest native canid in South America | Statement: [culpeo, bodySizeRelativeToOtherCanids, second-largest native canid in South America]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bodySizeRelativeToOtherCanids Context triple: [culpeo, bodySizeRelativeToOtherCanids, second-largest native canid in South America]
-
A.
canineSize
chosen
Indicates the relative physical size or stature of a canine in comparison to other canines or a defined standard.
-
B.
canineSizeRelativeToApes
Indicates how the size of an entity’s canine teeth compares to those of apes, typically in relative or proportional terms.
-
C.
sizeRelativeToOtherLeopards
Indicates how an individual leopard’s size compares to that of other leopards.
-
D.
eyeSizeRelativeToSkull
Indicates the comparative size of an entity’s eye(s) relative to the overall size of its skull.
-
E.
bodySize
Indicates the relative physical magnitude or scale of an entity’s body, such as how large or small it is.
- 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_69f76e9894208190a129a553a60ca58c |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fcd313e61c8190b174b331365b803f |
completed | May 7, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69fcd1f6b2e08190bf0300ae7c9ae67a |
completed | May 7, 2026, 5:55 p.m. |
Created at: May 3, 2026, 4:31 p.m.