Triple
T13729260
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | vaquita marina |
E329747
|
entity |
| Predicate | tamañoRelativo |
P8238
|
FINISHED |
| Object | una de las marsopas más pequeñas del mundo |
—
|
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: una de las marsopas más pequeñas del mundo | Statement: [vaquita marina, tamañoRelativo, una de las marsopas más pequeñas del mundo]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tamañoRelativo Context triple: [vaquita marina, tamañoRelativo, una de las marsopas más pequeñas del mundo]
-
A.
hasRelativeSize
chosen
Indicates that one entity’s size is being compared to another entity’s size, expressing a relative rather than absolute magnitude.
-
B.
relativeLength
Indicates a comparative relationship between entities based on how long they are relative to one another.
-
C.
relativeSizeOnTethys
Indicates how the size of one entity compares to another specifically in the context of Tethys.
-
D.
pyramidRelativeSize
Indicates how the size of one pyramid compares relative to another pyramid.
-
E.
surfaceAreaRelative
Indicates the ratio or comparative measure of one entity’s surface area relative to another reference surface area.
- 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_69d80772315881908f980cae40d91664 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69de01f746cc8190abde237bbb7e6c78 |
completed | April 14, 2026, 8:59 a.m. |
| PD | Predicate disambiguation | batch_69dbbe950b148190ba0df8a749269ec6 |
completed | April 12, 2026, 3:47 p.m. |
Created at: April 9, 2026, 9:55 p.m.