Triple
T27839219
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | African spoonbill |
E703633
|
entity |
| Predicate | typicalGroupName |
P62073
|
FINISHED |
| Object | colony |
—
|
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: colony | Statement: [African spoonbill, typicalGroupName, colony]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalGroupName Context triple: [African spoonbill, typicalGroupName, colony]
-
A.
typicalGroup
chosen
Indicates that the subject belongs to or represents a standard, characteristic, or commonly occurring group associated with the object.
-
B.
commonNameGroup
Indicates that multiple entities share the same commonly used name or are grouped under a single common name.
-
C.
groupDenotedBy
Indicates that one entity is the group collectively referred to or represented by another entity (such as a name, label, or expression).
-
D.
commonGroup
Indicates that the related entities belong to or participate in at least one group in common.
-
E.
identifiesGroup
Indicates that one entity serves to recognize, label, or distinguish another entity as belonging to a particular group or category.
- 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_69ef840d9e3c819093615ebff4ec22be |
completed | April 27, 2026, 3:43 p.m. |
| NER | Named-entity recognition | batch_6a00233e2170819084bee0c8f74cc1a4 |
completed | May 10, 2026, 6:18 a.m. |
| PD | Predicate disambiguation | batch_6a0022943fd08190b73007f080d5971d |
completed | May 10, 2026, 6:15 a.m. |
Created at: April 27, 2026, 6:01 p.m.