Triple
T2383718
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Asia |
E46368
|
entity |
| Predicate | hasSiblingGroup |
P26016
|
FINISHED |
| Object | three thousand Oceanids |
—
|
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: three thousand Oceanids | Statement: [Asia, hasSiblingGroup, three thousand Oceanids]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSiblingGroup Context triple: [Asia, hasSiblingGroup, three thousand Oceanids]
-
A.
hasRelatedGroup
chosen
Indicates that one group or collection is associated with another group or collection through some defined relationship or connection.
-
B.
sisterGroup
Indicates that two groups share an immediate common ancestor in a hierarchy or classification, making them each other’s closest related group.
-
C.
hasCommonAncestryGroup
Indicates that the related entities share membership in the same ancestral or lineage-based group.
-
D.
hasStepSibling
Indicates that one person is the step-sibling of another, meaning they are related through the marriage of their parents rather than by blood or adoption.
-
E.
hasSisterSubsystem
Indicates that one subsystem is related to another as a sister subsystem, meaning they share a common parent system or hierarchical level.
- 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_69a88a1554a48190a0180682bcf099be |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abc7bc87d0819090cd9d19d748bcc3 |
completed | March 7, 2026, 6:37 a.m. |
| PD | Predicate disambiguation | batch_69abc59f73f08190924a36d7d475d8f4 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:57 p.m.