Triple
T27208718
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cercopithecoidea |
E683941
|
entity |
| Predicate | hasNostrils |
P78829
|
FINISHED |
| Object | narrow downward-facing nostrils |
—
|
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: narrow downward-facing nostrils | Statement: [Cercopithecoidea, hasNostrils, narrow downward-facing nostrils]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNostrils Context triple: [Cercopithecoidea, hasNostrils, narrow downward-facing nostrils]
-
A.
nostrilOrientation
chosen
Indicates the directional alignment or facing angle of an entity’s nostrils relative to a reference frame or axis.
-
B.
nostrilPlacement
Indicates the spatial position and orientation of an entity’s nostrils relative to its head or face.
-
C.
usesNasalSacFor
Indicates that an entity employs a nasal sac as a functional tool or mechanism for a specific purpose or activity.
-
D.
noseLength
Indicates the length or size of an entity’s nose, typically as a measurable physical attribute.
-
E.
hasColorOfNose
Indicates that one entity possesses a nose whose color matches or is characterized by the specified color 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_69eefad339a08190aeacb2a198f1a39b |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69fe610e1f6881908f10070ba64643cf |
completed | May 8, 2026, 10:17 p.m. |
| PD | Predicate disambiguation | batch_69fe604c6c008190ad659e9b9fa82f7b |
completed | May 8, 2026, 10:14 p.m. |
Created at: April 27, 2026, 9:38 a.m.