Triple
T28494242
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tanasi |
E721060
|
entity |
| Predicate | associatedWithSubgroup |
P182000
|
FINISHED |
| Object | Overhill Cherokee |
—
|
NE NERFINISHED |
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: Overhill Cherokee | Statement: [Tanasi, associatedWithSubgroup, Overhill Cherokee]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedWithSubgroup Context triple: [Tanasi, associatedWithSubgroup, Overhill Cherokee]
-
A.
subgroupOrRelated
chosen
Indicates that one entity is a subgroup of, or otherwise closely related in group membership or classification to, another entity.
-
B.
revealedAsSubgroupOf
Indicates that one group has been newly identified or exposed as being a subgroup or subset of another group.
-
C.
subGroupOf
Indicates that one group is a subset or specialized division of another, larger group.
-
D.
usesSubgroup
Indicates that one entity employs, incorporates, or operates through a specific subgroup of another entity or system.
-
E.
sharesSubgroupWith
Indicates that two entities belong to at least one common subgroup within a larger grouping or classification.
- 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_69f01a5afdac8190ac6e72d5c100bd58 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_6a016b2629c48190befb10581560d58f |
completed | May 11, 2026, 5:37 a.m. |
| PD | Predicate disambiguation | batch_6a0167d5a2088190a68dbd2b87f73e80 |
completed | May 11, 2026, 5:23 a.m. |
Created at: April 28, 2026, 3:03 a.m.