Triple
T19771360
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Google+ Circles interface |
E474894
|
entity |
| Predicate | supportsTypeOfGrouping |
P100155
|
FINISHED |
| Object | family circle |
—
|
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: family circle | Statement: [Google+ Circles interface, supportsTypeOfGrouping, family circle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsTypeOfGrouping Context triple: [Google+ Circles interface, supportsTypeOfGrouping, family circle]
-
A.
supportsGroupType
chosen
Indicates that one entity is compatible with or able to support a particular category or type of group.
-
B.
groupingType
Indicates how multiple entities are categorized or clustered together based on a shared grouping criterion.
-
C.
supportsType
Indicates that one entity is capable of handling, accepting, or being compatible with a specified type.
-
D.
appliedToGroupType
Indicates that something (such as a rule, setting, or action) is applied specifically to a particular type or category of group rather than to individual members.
-
E.
hasGroupStructure
Indicates that the related entities together form an algebraic group under a specified operation, satisfying closure, associativity, identity, and invertibility.
- 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_69d8e51a43a08190956bc6df13c91a77 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6535bd8c0819097671783962b6bc5 |
completed | April 20, 2026, 4:25 p.m. |
| PD | Predicate disambiguation | batch_69e53053ed2881908400becdfada7fd3 |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 1:48 p.m.