Triple
T16230220
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Syncerus |
E393957
|
entity |
| Predicate | includesOrganismsWithTrait |
P54237
|
FINISHED |
| Object | large body size |
—
|
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: large body size | Statement: [Syncerus, includesOrganismsWithTrait, large body size]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesOrganismsWithTrait Context triple: [Syncerus, includesOrganismsWithTrait, large body size]
-
A.
containsSpeciesWithTrait
chosen
Indicates that a collection or group includes at least one species that exhibits a specified trait.
-
B.
belongsToSpeciesWithTrait
Indicates that an entity is a member of a species that possesses a specified trait.
-
C.
hasOrganism
Indicates that one entity is an organism associated with, contained in, or otherwise possessed by another entity.
-
D.
includesSpecies
Indicates that one entity contains or encompasses one or more species as part of its composition or scope.
-
E.
includesSpeciesFrom
Indicates that one collection, group, or set contains one or more species that originate from or belong to another specified source or context.
- 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_69d87f204df88190a8f88923decf9835 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e23d29438c81909aa2724cc47bb959 |
completed | April 17, 2026, 2:01 p.m. |
| PD | Predicate disambiguation | batch_69e219e94a448190b73a4e6aa374eb4a |
completed | April 17, 2026, 11:30 a.m. |
Created at: April 10, 2026, 5:03 a.m.