Triple
T26110294
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Buru babirusa |
E658672
|
entity |
| Predicate | tuskType |
P87400
|
FINISHED |
| Object | upper canines grow upward through the snout |
—
|
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: upper canines grow upward through the snout | Statement: [Buru babirusa, tuskType, upper canines grow upward through the snout]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tuskType Context triple: [Buru babirusa, tuskType, upper canines grow upward through the snout]
-
A.
hasTusk
Indicates that an entity possesses one or more tusks as a physical feature.
-
B.
hasTuskMaterial
Indicates that an entity’s tusks are made of, or composed from, a specified material.
-
C.
tuskGrowthDirection
chosen
Indicates the direction in which an entity’s tusks grow or extend relative to its body.
-
D.
spurType
Indicates the specific kind or category of spur associated with or used by an entity.
-
E.
nutType
Indicates the specific kind or category of nut associated with an entity.
- 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_69ee5bc20298819099a42be042eb2349 |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f6077b10108190b1842436b70f8985 |
completed | May 2, 2026, 2:17 p.m. |
| PD | Predicate disambiguation | batch_69f5b0021da88190bdd4cf2698c23edf |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 26, 2026, 8:01 p.m.