Triple
T16110170
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Polistes annularis |
E390850
|
entity |
| Predicate | casteSystem |
P90994
|
FINISHED |
| Object | queen and worker castes |
—
|
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: queen and worker castes | Statement: [Polistes annularis, casteSystem, queen and worker castes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: casteSystem Context triple: [Polistes annularis, casteSystem, queen and worker castes]
-
A.
hasCasteSystem
chosen
Indicates that a society or group is organized into a hierarchical caste system that assigns people to fixed social strata.
-
B.
hasCaste
Indicates that an entity belongs to or is associated with a particular caste within a social or hierarchical system.
-
C.
associatedWithCaste
Indicates a relationship where an entity is linked or connected to a particular caste, typically by social, cultural, or hereditary association.
-
D.
nobilitySystem
Indicates a social or political structure in which individuals are ranked by hereditary titles or noble status.
-
E.
hatteBevölkerungssystem
Indicates that an entity possessed or was characterized by a particular population system (e.g., a specific way its population was structured, organized, or administered).
- 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_69d87f1a8dd881909f1de6ef78849874 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e2016665c0819081aa7a44b1d08183 |
completed | April 17, 2026, 9:46 a.m. |
| PD | Predicate disambiguation | batch_69e1828518c48190a8ef3aaa46a1f639 |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 5 a.m.