Triple
T2118571
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bos indicus |
E43862
|
entity |
| Predicate | skinPigmentation |
P13150
|
FINISHED |
| Object | often pigmented to protect from UV |
—
|
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: often pigmented to protect from UV | Statement: [Bos indicus, skinPigmentation, often pigmented to protect from UV]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: skinPigmentation Context triple: [Bos indicus, skinPigmentation, often pigmented to protect from UV]
-
A.
pigmentation
chosen
Indicates the presence, type, or degree of coloration in or on an entity.
-
B.
skinCharacteristic
Indicates a relationship where an entity is associated with a particular quality, feature, or condition of its skin.
-
C.
secondaryPigment
Indicates that one pigment functions as a secondary or supporting color relative to another primary pigment in a given context.
-
D.
primaryPigment
Indicates that one pigment is the main or dominant colorant used or present in relation to another entity.
-
E.
skinThickness
Indicates the measured thickness of an entity’s skin, typically quantifying how thick its outer tissue layer 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_69a88717cfe48190b7ecdd68c824848a |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abbb3117c081908c5e748a869d1f9f |
completed | March 7, 2026, 5:44 a.m. |
| PD | Predicate disambiguation | batch_69abb7bbf9d881909d223b0cab7cab18 |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:44 p.m.