Triple
T24921320
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Guang |
E618731
|
entity |
| Predicate | hasHigherFamily |
P162555
|
FINISHED |
| Object | Kwa (in some classifications) |
—
|
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: Kwa (in some classifications) | Statement: [North Guang, hasHigherFamily, Kwa (in some classifications)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHigherFamily Context triple: [North Guang, hasHigherFamily, Kwa (in some classifications)]
-
A.
hasHigherFamily
chosen
Indicates that one entity belongs to a family or familial group that is ranked or positioned above another entity’s family in a hierarchy or comparative structure.
-
B.
hasHigherClass
Indicates that one entity belongs to a higher rank, level, or category in a hierarchy than another entity.
-
C.
containsFamily
Indicates that one entity includes or encompasses members of a particular family group within it.
-
D.
hasHierarchyAbove
Indicates that one entity occupies a higher or superior level in an ordered structure or chain of command relative to another entity.
-
E.
hasHigherInstance
Indicates that one instance in a hierarchy or ordering is ranked or valued higher than another instance.
- 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_69e2fab9edd88190b86004a78a28bc20 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f6352fdb788190b9bad30243690743 |
completed | May 2, 2026, 5:32 p.m. |
| PD | Predicate disambiguation | batch_69f63182f1408190bddc1214fcbd6145 |
completed | May 2, 2026, 5:16 p.m. |
Created at: April 18, 2026, 5:28 a.m.